Cloud routine outcomes config creates a feature branch, so the agent commits and pushes there instead of main. Fix: remove outcomes + add explicit git checkout main in skills. Also hit a list API pagination bug (cursor never advances) along the way.
Looplane now grades effects as read/modify/modify_execute/execute and fails closed on unclassified tools. Native MCP tools default to execute unless trusted read-only metadata lowers them. Approval events still land in events.jsonl first and grants can scope to one change set or backend; general command rules and universal sandbox coupling remain unfinished.
Mature-agent compaction must handle triggers, complete-turn cut points, and recovery. looplane now has an 85% high-watermark, automatic compaction, a deterministic native-loop fallback summary, persisted checkpoints, and workspace-context reinjection. Cross-runtime fallback, model-quality summaries, and live-provider long-session validation remain open.
omp and claude-code provide cross-session memory while the other references mostly rely on instruction files. looplane now has an explicit remember/list/inject baseline: typed JSONL memories enter prompts across sessions, but retrieval is scope-and-recency only, with no semantic ranking, deduplication, forget command, or automatic extraction.
All five projects combine allow/ask/deny decisions, compound-command inspection, and fail-closed behavior. looplane now has a deny-first classifier, critical floor, shell segmentation, timeout-deny, configured allow/deny rules, and visible policy reasons. Broader syntax coverage and live interactive validation remain open.
Hooks govern control flow, skills inject knowledge, and plugins package both. looplane now has opt-in deny-only project hooks, a bounded SKILL.md loader, exact enabled_skills selection, plugin manifests/install/list, and external-runtime projection. Input rewriting, full lifecycle coverage, remote registries, and a mature marketplace remain open.
looplane can now inject repository diagnostics and open-file state into the next model turn, push typed IDE context over WebSocket, package a VS Code bridge, and supervise long-lived LSP subprocesses through ManagedLspServer. Language-specific initialize/didOpen/didChange adapters and live-editor validation remain open.
Mature subagents need roles, bounded fan-out, narrowed permissions, and a result contract. looplane now has native named-role schedules, parallel fan-out, child allowed_paths constrained by the parent, unsafe execution disabled by default, and parent-approved transaction proposals. Persistent background lifecycles, recursion trees, and automatic worktree merging remain open.
Looplane's core surface has grown from seven tools to nine with a read-only `tool_program` and rollback-capable `tool_transaction`; search prefers ripgrep and arbitrary shell remains absent. Native MCP tools join only from allowlisted servers and default to execute approval without trusted read-only metadata.
`ExternalCodingRunner` is Looplane's second runtime lane. The external coding CLI owns its model loop and credentials; Looplane hands off a task and disposable clone, then treats the returned patch as untrusted input and reruns path audit, verification, and the source invariant. This is a capability-bounded handoff, not another `ModelProvider`.
Moshi is an iOS/Android terminal app (plus a free Moshi Desktop web UI) that connects over SSH/Mosh straight to your own machine to drive Claude Code, Codex, and other coding agents. The free tier is a complete terminal; Pro ($7.99/mo and up) unlocks Mosh's connection resilience, deep tmux integration, and the diff viewer.
Four philosophies of ADE workspaces: arul28/ADE's Brain+Lane, Superset's 100-agent IDE, Herdr's Rust-native runtime, and Kadro/Orca's pane and Fleet angles — compared in one table with a decision tree for when to pick a workspace over an Omnigent-style control plane.
Databricks' open-source Omnigent wraps Claude Code, Codex, Cursor, Pi and custom agents in a Runner/Server + Omnibox sandbox, adding three-layer Policies and shareable persisted Sessions so you can swap models and harnesses with one-line changes — 9.3k stars, still alpha.
`claude agents` gives you one screen listing every background session, with Needs input, Ready for review, Working, Completed, and related states managed in one table. Press Space to peek, Enter to attach. Combined with cross-session messaging (ListAgents / SendMessage, v2.1.224+), sessions can also message each other; same-machine delivery uses a local socket and never touches Anthropic servers.
Claude Code splits its configuration across the project `.claude/` folder and your home directory — 20+ file locations. Only two mental models matter: settings merge across layers and are enforced; CLAUDE.md and rules concatenate into context as guidance. And every file is committed, gitignored, or Claude-written.
After GitHub PR review is configured, a fleet of agents reviews PRs according to the repo's trigger mode — 20 minutes on average, about $15–25 per review, with findings posted as inline comments on the offending lines. For larger changes, /code-review ultra launches a cloud deep review that reports independently verified bugs in 5–10 minutes at roughly $5–25 per run; Pro/Max plans include 3 free runs.
Claude Code costs accumulate with context size: enterprise deployments average ~$13 per developer per active day and $150–250 per month. This post covers /usage and /insights tracking, six token-saving tactics, and a systematic answer to 'which model should I use': provider-dependent model aliases, effort levels, fast mode ($10/$50 per MTok for Opus 5/4.8), and the advisor tool.
When CLAUDE.md rules are ignored, hooks never fire, or an MCP server shows no tools, the file usually didn't load, loaded from an unexpected location, or got overridden. This guide covers what the diagnostic entries (/context, /memory, /skills, /doctor, /mcp, and more) actually show, safe-mode bisection, and a table of six high-frequency error messages with fixes.
Add Anthropic's official Dev Container Feature (`ghcr.io/anthropics/devcontainer-features/claude-code:1.0`) to `.devcontainer/devcontainer.json` and three steps—write the config, rebuild the container, run `claude` to sign in—put every teammate's Claude Code behind the same container definition. The same definition feeds GitHub Codespaces and CI; a five-step rollout gets the whole team there.
Dynamic workflows let Claude write multi-agent orchestration as a JavaScript script that a runtime executes in the background — up to 1,000 agents per run, savable as a /<name> command. This piece covers trigger methods, the save-and-rerun flow, three fit scenarios (codebase audit, large migration, cross-checked research), and where they differ from Agent Teams.
Claude Code runs an agentic loop — gather context, take action, verify results — until the task is done. This entry to the series breaks down its five tool categories, the model/harness split, and the two safety rails: checkpoints and permission modes.
The official docs split Claude Code's parallel work into 4 approaches: subagents delegate inside one session, agent view lets you supervise background sessions yourself, agent teams coordinate workers through a lead, and dynamic workflows run scripted fleets of subagents with cross-checks; file collisions are always handled by worktrees. Includes a translated comparison table and a three-question decision guide.
Claude Code on the web runs tasks in cloud environments, Anthropic-managed VMs by default or self-hosted environments when routed there: authorize GitHub, dispatch from browser or mobile, start cloud sessions with --cloud, and pull them back local with --teleport. Research preview on Pro/Max/Team; no separate compute charge, but rate limits are shared.
Claude Code ships six permission modes; day to day you cycle Manual, Accept edits, Plan, and Auto with Shift+Tab. On Pro/Max/Team plans, eligible interactive terminal and VS Code sessions start in auto mode by default, with a background classifier reviewing most actions and blocking force pushes, `curl | bash`, production deploys, and more by default. This post covers the four-mode spectrum, permission rule syntax, and organization-level trust config.
Claude Code's prompt caching works by exact prefix matching: a cache read bills at roughly 10% of the standard input rate, but switching models, changing effort, enabling fast mode, toggling MCP servers, or denying an entire tool forces the next turn to reprocess everything. The TTL defaults to five minutes; the main conversation and a few helper requests on a subscription get one hour.
Claude Code writes every session line by line to a JSONL file under ~/.claude/projects/, kept for 30 days by default. This post breaks down --continue vs --resume, session naming rules, /branch fork semantics, and transcript export and cleanup settings.
Work through install and login failures in five steps: verify PATH on your OS, confirm there is only one installation, test downloads.claude.ai for a 200, recover failed OAuth callbacks by pasting the login code or using claude auth login, then finish with claude doctor.
Five classes of runtime fixes: diagnose high memory with /compact plus /heapdump; recover a hung session with Ctrl+C and claude --resume; write large tables to files instead of forcing terminal output; escape autocompact thrashing by reading files in chunks or running /compact with a focus; fix broken search by installing system ripgrep and setting USE_BUILTIN_RIPGREP=0.
BytePlus ModelArk Coding Plan offers Lite ($10/month) and Pro ($50/month) subscriptions covering models such as DeepSeek-V4, GLM-5.2, and Seed-2.0 in tools including Claude Code and Cursor. Lite includes about 24,000 requests per month; Pro includes five times as many.
pi's loop is a double while-loop wrapped in an EventStream; claude-code's source openly says stop_reason is unreliable and uses tool_use blocks observed during streaming as the sole continue signal; codex models a turn as a cancellable SessionTask and records sessions with a dedicated rollout crate. looplane chose an ordering — manifest first, JSONL second — that turns Ctrl-C into verified resumption instead of a rerun. All evidence cited at file#symbol level.
Mature coding-agent CLIs have converged on the same conventions: positional prompt, -p means print, exec is headless, resume is a first-class command, -C changes directory; looplane inherits this vocabulary directly, driving learning cost close to zero.
Every mature coding agent ships a machine interface: codex has `exec --json` plus a full app-server JSON-RPC protocol, claude-code has `-p` with stream-json, and pi/opencode/omp each expose a JSON event stream. Wrapping these CLIs as your backend is the fastest path to subscription-backed coding — but they own their agent loop, their login, and their permission model. looplane's answer: let the external CLI fully own its loop while looplane holds only three things — an isolated working copy, patch audit, and final verification. One runtime never impersonates another.
The biggest problem when an agent enters CI is approval: no TTY, nobody to click approve. The five reference projects converge on two strategies — delegate permission decisions to the calling program (claude-code's control protocol), or replace approval semantics entirely (codex defaults to Never plus sandboxing, opencode auto-rejects). looplane keeps one AgentRunner loop and injects a different ApprovalPolicy: headless uses HeadlessApprovalPolicy, which never reads stdin so it cannot hang the pipeline, and denies EXECUTE by default — fail closed.
A blank config file drives people away; a bad credential discovered too late drives them away faster. All five mature agents treat setup as a first-class state, and looplane adds the step most of them skip: verify the key right after saving it.
All five agents store sessions as append-only JSONL plus some form of single-writer protection, but crash recovery lives in the details: pi repairs torn tails, codex reopens and retries after write failures, and looplane picked a 'manifest first' ordering that reduces the only crash window to one repairable slot. This post dissects each project's write ordering and fail-closed conditions, all cited at file#symbol level.
Mature coding agent TUIs never print the event stream directly — they build a typed projection layer first and update it in place. looplane took three steps (full-screen composition, runtime-first dual modes, removing the Ask/Agent split) before two old constraints — non-streaming output and resume-without-replay — were truly lifted.
Anthropic interviewed 15 startups and distilled five Claude Code operating principles: everyone ships, automate the tedium, trust but verify, build for rebuilding, prototype to productionize. ClickHouse shipped 30% more features, Clay automated 100% of bug triage, Artemis Security hit 6,000+ PRs per week.
A Claude Code- or Codex-style TUI depends on long-lived sessions, typed transcripts, and approval at tool boundaries—not a screen full of color.
In August 2026, it's not just five frameworks moving. Beyond OMP 2, Pi v2, Opencode 2, dsh, and Claude Code, three model makers — Google (Antigravity CLI), Meta (Muse Code), and xAI (Grok Build) — are building coding agents directly. Add Amp, Cline 2.0, and the Codex CLI Rust rewrite, and eight-plus frameworks are undergoing architecture-level changes simultaneously. Factor in 110+ total CLI tools, and H2 2026 is a divergence period for harness methodology. This article analyzes four architectural approaches, one shared direction, and one emerging trust crisis.
Slack Code moves AI coding agents from individual terminals into shared Slack channels where teams can see diffs, previews, and plans in real time. But it solves management's visibility anxiety, not engineers' productivity bottleneck — the real battle is over who becomes the agent control plane.
I turned Anthropic's session-cost advice into a global skill, and the first version made the very mistakes it was meant to prevent: a description stuffed with trigger keywords, hard thresholds based on file counts and minutes, and 'protect the main context' conflated with 'spend fewer tokens overall'. Three rounds later the entry point is one page, details live in references, numeric thresholds became four judgment dimensions, and every claim from a draft post was checked against official docs.
Chroma's controlled study shows that even when it fits, a full context degrades performance. Coding agent vendors have landed on seven different responses: compact, hand off, prune, defer loading, isolate, train it into the model, or change the unit of work. Amp removed /compact outright, Atlassian argues summarization should be a last resort, and Cursor's A/B test measured a 46.9% token reduction. The three real disagreements come down to what each team is measuring.
A complete study guide for Claude's official architect certification (CCAR-F): five domains weighted 27/18/20/20/15, four scenarios drawn from six, common anti-patterns, and hands-on preparation. Official specs are 60 items / 120 minutes / $125 / 12-month validity / 720 to pass; registration is limited to Claude Partner Network members, and on-time renewal is free and non-proctored.
`hermes claw migrate` imports persona, memory, skills from four locations, model and provider config, platform tokens, and the approval allowlist — but secrets are never imported silently, and even `--preset full` requires an explicit `--migrate-secrets`. What can't move (cron jobs, plugins, hooks, the multi-agent list, deep channel config) isn't discarded but parked in `~/.hermes/migration/openclaw/<timestamp>/archive/` for manual work. Coming from Claude Code or Codex is a different command: `hermes import-agent`.
A VS Code extension open-sourced by Microsoft employees that reads your local Claude Code / Codex / OpenCode session logs. The real payload is 45 Markdown rules: prompts under 30 characters, sending the next message within 15 seconds of receiving 20 lines of AI code, instruction files over 4,000 bytes — turning 'context engineering' into numbers you can argue with.
The course lists four techniques for directing agents: instruction files, hooks, commands, subagents. The instruction file is the only one loaded in full every startup, making it config rather than memory; hooks cover what instructions can't, because a rule can be ignored and a hook cannot; commands are the only one a human triggers. The course also marks just one and a half of seven task steps as human work.
Week 1 of CS146S is 'build Claude Code in 200 lines' plus a dissection of production system prompts. The agent loop really is that small. The course slides close with four things Claude does underneath, one of them being `<system-reminder>` tags scattered everywhere to stop the model drifting — which appears in no official documentation.
The Agent Skills spec fits in a sentence: a directory containing a SKILL.md. The real design is three levels of progressive disclosure — only name and description load at startup, the body loads on a match, bundled files load on demand. This site's own repo carries 35 skills and 7,893 lines of SKILL.md, and startup still costs only those 35 metadata pairs.
Stanford CS146S's Fall 2026 syllabus compresses prompting from a full week into a single bullet, drops the terminal and UI-generation weeks, and adds Agent Skills, Agent-Ready Codebases, Background Agents, and AI-Native Team. Grading moved too: the final project fell from 80% to 50%, with 30% now on open source contributions. This series reads all ten weeks.
Every official course platform from OpenAI, Anthropic, and Google, plus Stanford CS146S/CS336, Elements of AI, Hugging Face, MIT 6.S191 and more — scraped page by page, then re-sorted into four tiers: AI-curious, vibe coding, shipping to production, and how models actually work. Also covers self-study repos still being updated in 2026 and browser-based platforms that need no local setup, filtered by last-commit date rather than star count. The conclusion: nearly all of it is free. What is scarce is not courses, it is the judgment to pick one. And tier four will not fix your tier three problem.
Loop Engineering is the practice of designing systems that automatically prompt AI agents, rather than prompting them manually. Boris Cherny runs hundreds of agents, Addy Osmani coined the term, and Blake Crosley identified verification cost as the real bottleneck — this article covers primary sources, the five building blocks, applicability boundaries, and criticisms.
AI agents running tests are non-reproducible; hand-written Playwright is hard to maintain. Four tools that emerged in 2024-2025 each tackle this dilemma with very different design philosophies.
CodeGraph uses tree-sitter to extract a codebase into a local SQLite/FTS5 knowledge graph, letting AI coding agents query the graph instead of scanning files. The official end-to-end benchmark (7 repos, median of 4 runs) averages 35% cost savings and 70% fewer tool calls -- but only if the agent actually walks the graph. Delegating exploration to a file-reading subagent that ignores CodeGraph turns it into pure overhead.
Anthropic shipped Claude Design on 2026-04-17. On 4-28, nexu-io/open-design went public -- same artifact-first loop, Apache-2.0, runs on the 16 coding-agent CLIs you already have. Two weeks from 0.1 to 0.7, 40k+ stars. A paradigm shift that flattens AI design tools from vertical SaaS into a skill bundle.
AI agents can operate video generation tools through three approaches — Skills, MCP Connectors, and direct APIs. Choosing the right integration method matters more than choosing the right tool.
A survey of 11 public LLM writing pipelines, distilled into three dominant patterns: multi-agent (researcher -> writer -> critic), Karpathy LLM-wiki (raw + wiki + LLM writes, humans don't), and quality guardrails (technical verifier + never fabricate + brief gate). The Princeton GEO paper (KDD 2024) quantifies the impact: inline citations +28%, adding statistics +33%, quoting source text +41%, keyword stuffing -9%.
Spin up a local OpenAI-compatible endpoint at localhost:20128 that automatically routes requests from Claude Code / Cursor / Cline / Codex / Copilot through a Subscription → Cheap → Free 3-tier fallback to 40+ providers. Built-in RTK compresses tool_result (saving 20–40% input tokens), Caveman mode compresses output, OAuth auto-refresh, multi-account round-robin — install with npm install -g 9router and two commands.
Stripe Minions says 'The walls matter more than the model,' but the case studies from four Silicon Valley companies never explained how to actually build those walls. This post breaks down the 15 walls we implemented in the daodao auto-dev agent: what each wall prevents, where the files live, and what the tradeoffs are. Tier 1 is mandatory, Tier 2 strengthens governance, Tier 3 is serious governance.
Build a Notion task → GitHub issue → spec PR → code PR auto-dev agent from scratch. Using the daodao case as a template, this guide walks through every step — what to do, what to verify, and how to handle problems. Notion DB schema → bin/ scaffold → two Claude Code routines → cloud env vars → staging tests.
5 rounds of consensus to write the plan, then team mode with 5 workers running 12 tasks in parallel — with plenty of pitfalls along the way. Writing it down for my future self and anyone else trying the same thing.
/loop is Claude Code's native cron feature — set schedules in plain English and let Claude monitor, auto-fix PRs, and run recurring tasks in the background. Session-scoped and expires after 7 days; for cross-session scheduling, use Routines or Desktop scheduled tasks.
Routines is Claude Code's cloud automation system (formerly Cloud Scheduled Tasks). Beyond cron scheduling, you can trigger runs via API endpoint or GitHub events — scan issues, review PRs, run checks, open PRs — all while your computer is off.
When using AI agents like Claude Code or Cursor, built-in WebFetch / WebSearch often gets blocked by Cloudflare, geo-restrictions, or rate limits. Connecting a search MCP server is the most direct fix. This post compares the options actually available in 2026.
goose is an open-source AI Agent maintained by the Linux Foundation's AAIF, supporting 15+ LLM providers and 70+ MCP extensions, built with Rust as a Desktop App + CLI + API. It positions itself as a vendor-neutral, self-hostable alternative to Claude Code.
Cloudflare ran a Multi-Agent Code Review system internally for 30 days — 131K reviews, median 3 minutes. This post breaks down their architecture and compares it with solutions from Anthropic, GitHub, CodeRabbit, Greptile, and others.
AI models rationalize their own code when reviewing it. Using three different CLIs for independent review effectively catches blind spots -- this post covers the design philosophy and practical workflow patterns behind the approach.
Agentic AI is not just autocomplete — it is an AI system capable of autonomously executing multi-step tasks. This article breaks down the five phases of the SDLC, explaining where to plug in agents at each phase, how to progress from CLI tools to full-pipeline automation, and the most valuable external resources to track right now.
Encyclopedia of Agentic Coding Patterns catalogues 190 patterns to help you make the right software decisions in the age of AI-written code — and the book itself is autonomously written and maintained by an AI agent.
MCP is not going away, but its effective scope is narrower than most people think. For local development, CLI and raw API almost always beat MCP. MCP's truly irreplaceable niche is the narrow gap of 'cross-agent shared local tool layer.'
Different AI engines process web pages in vastly different ways. Some only read the body; others rely on pre-built indexes. JSON-LD and schema markup are not universally effective — body content quality and structure are the only cross-platform foundations that hold.
Claude Octopus is a Claude Code plugin that simultaneously calls Codex, Gemini, Copilot, Qwen, Ollama, Perplexity, OpenRouter, and Claude to review the same code, using a 75% consensus threshold to catch single-model blind spots. It ships with 32 personas, 48 /octo:* slash commands, 51 skills, and a Dark Factory fully autonomous spec-to-code pipeline.
Better Agent Terminal (BAT) is an Electron desktop app that unifies multiple project workspaces, terminals, and Claude Code Agents into a single window — solving the everyday pain of exploding iTerm tabs and the lack of a proper GUI container for agents. MIT License, available on macOS, Windows, and Linux.
Agent Skills is Addy Osmani's open-source collection of 19 production-grade engineering skills that drive AI agents to follow senior engineering discipline through /spec → /plan → /build → /test → /review → /ship commands, instead of cutting corners.
Graphify uses tree-sitter AST to extract code structure, then applies LLM semantic analysis to documents and images, compressing an entire project into a queryable knowledge graph. It claims to save 71.5x tokens per query compared to reading raw files.
Claw Code is a from-scratch Rust rewrite of the Claude Code CLI, featuring 48K lines of code, 40 tools, and MIT licensing. Most remarkably, the entire project was built by multiple AI agents collaborating over just 5 days, surpassing 170K GitHub stars within a week of launch.
oh-my-claudecode (OMC) adds 8 collaboration modes, 19 specialized agents, and cross-model orchestration (Claude + Codex + Gemini) on top of Claude Code, transforming a single-user CLI tool into a multi-agent development platform. Features include Deep Interview for requirement clarification, Smart Model Routing that saves 30-50% on tokens, and automatic rate limit recovery.
Claude Code only reads CLAUDE.md; Codex only reads AGENTS.md. Teams using both end up maintaining two identical files. Fix: make CLAUDE.md a symlink pointing to AGENTS.md — one source of truth.
There are already 6,400+ .claude/agents/*.md files on GitHub. We dissected 4 representative projects — ChemistryTimes (content production pipeline), claude-sub-agent (document-driven development pipeline), agentic (Temporal.io DAG parallel execution), and vs-copilot-multi-agent (hook-enforced memory persistence) — plus ruflo's enterprise-grade swarm architecture, distilling 6 design patterns and 5 practical trends.
Andrej Karpathy proposed a framework for compiling personal knowledge wikis with LLMs — collect raw data, have the LLM compile it into .md wiki pages, run Q&A against the wiki, and file outputs back. This post compares three practical approaches: Karpathy's knowledge vault model, the community's experience vault model, and quidproquo's blog model.
After dissecting Claude Code's 18+ caching mechanisms, I found that you can't touch provider-level prompt cache, but embedding cache, tool result cache, and entity cache are not only within your reach — they deliver even better results. Includes a complete AgentCache interface design and per-tool TTL strategy.
Every one of Claude Code's 45 tools uses a prompt() method that dynamically adjusts based on user type, feature flags, and system capabilities. Applying this pattern to a ReAct Agent, tool descriptions are dynamically generated along three dimensions: orchestrator model capability, locale, and available tools. Small models automatically get few-shot examples; large models save tokens.
Claude Code runs from $20/mo Pro to $200/mo Max 20x. Quota is a rolling five-hour window with weekly limits on top, shared across Claude on web, desktop, mobile, and the terminal. When you run out you can switch to usage credits at standard API rates rather than stopping.
A comparison of six agent CLI subscriptions (Claude Code, Cursor CLI, Codex, Kiro, Antigravity/Gemini CLI, OpenCode) plus the multi-model routing pattern — cheap models for simple work, strong models for hard work. Nearly every one of these changed its billing in the first half of 2026; this version was re-verified on 8/18.
Skill paths are almost always runtime-specific. AGENTS.md is the reliable way to share rules across agents. Put personal reusable capabilities in each agent's supported global directory; put project workflows inside the repo.
Agent CLIs are not smarter autocomplete tools -- they are AI agents that can read your codebase, execute multi-step tasks, and operate in real environments. Claude Code, Codex CLI, Gemini CLI, OpenCode, Aider, Pi, Kiro, Amp, Cursor CLI... the tools keep multiplying, but they all share a common set of design principles -- understanding these principles is how you actually get good at using them.
Use Claude Code as an orchestrator to chain Playwright screenshots, catbox.moe image hosting, Meta Graph API publishing, and Telegram notifications — generate and publish an IG carousel from a single sentence.
Claude Code is Anthropic's agentic coding tool that runs in the terminal, IDEs, Slack, GitHub, and on the web. Its core extension system has six layers: CLAUDE.md (persistent context), Skills (on-demand workflows), Hooks (deterministic automation), Subagents (isolated delegation), MCP (external tool connections), and Agent Teams (multi-agent collaboration).
A Skill is a prompt template you invoke manually. A Subagent is an independent agent that Claude routes to automatically. They look similar, but differ completely in trigger mechanism, tool isolation, and context management.
When processing requests, Claude Code randomly displays one of 185 built-in verbs (like Thinking, Brewing, Clauding), then picks one of 8 completion verbs with elapsed time. You can customize these via spinnerVerbs in settings.json, using either replace or append mode. All data in this post is verified directly from cli.js source code.
gstack is Garry Tan's open-source Claude Code skills toolkit. Its 20 specialized skills transform a solo developer into an entire engineering team — automating everything from product planning and design review to code review, QA, and deployment.
The model is the CPU, the harness is the operating system, and the agent is the application. No matter how powerful a model is, without a good harness it's just a demo. Phil Schmid argues that harness is the most critical infrastructure in AI engineering for 2026.
The original Claude Code troubleshooting collection has been split into orders 33-35: installation & login, runtime problems, and config diagnosis. This page is their index.
Agent Teams lets multiple full Claude Code sessions work as one team: a team lead assigns work while teammates each run their own context window, coordinating through point-to-point messaging and a shared task list. This post covers the three key differences from sub-agents, the trade-off between teammateMode display modes, and why token cost scales linearly with team size.
Anthropic's official Claude Code best practices boil down to one constraint: manage the context window. This post reorganizes their guidance into a working loop — explore, plan mode, implement with a runnable check, verify, commit — plus prompt techniques, when to /clear vs rewind, and the five failure patterns they call out.
Channels are a special kind of MCP server that push CI failures, monitoring alerts, and Telegram messages directly into a running Claude Code session — and Claude can answer back through the same channel via a reply tool. This post breaks down the channel contract, two-way replies, security gates, and install requirements.
Checkpointing is not git commits: Claude Code snapshots your files before every user prompt, keeps the 100 most recent per session, and deletes them after 30 days. This piece breaks down the five rewind menu options, the tracking boundaries (bash, subagents, symlinks), and how checkpoints divide labor with git.
Claude Code gains browser control through the Claude in Chrome extension: read console logs and DOM state, click, type, upload files, record GIFs, and operate sites you're already signed into. The official prerequisites list Chrome, Edge, and Chromium-based browsers such as Brave, Arc, Vivaldi, and Opera, but WSL is not supported.
Put Claude Code into GitHub Actions with anthropics/claude-code-action: /install-github-app sets everything up in one command, @claude in a PR or issue comment gets bugs fixed, branches pushed, and PR creation links returned; Bedrock/Vertex/Foundry backends switch via one input with OIDC and no stored keys; the GitLab CI/CD integration (beta) mirrors it as a single .gitlab-ci.yml job where every change flows through a merge request.
Every Claude Code session starts with a clean context window. Three memory mechanisms carry knowledge across sessions: CLAUDE.md files loaded every session, .claude/rules/ files that load conditionally via paths frontmatter, and auto memory Claude writes itself. All CLAUDE.md layers are concatenated into context — not inherited by override. This guide covers layer behavior, @path imports, monorepo strategies with nested CLAUDE.md, and sharing one instruction file across tools via @AGENTS.md.
Claude Code loads the system prompt, MEMORY.md, CLAUDE.md, MCP tool names, and skill descriptions before you type your first word. This post breaks down the startup context, what each of six extension features costs, and how to control auto-compaction with /compact, /autocompact, and autoCompactWindow.
Claude Code's built-in sandboxed Bash restricts every command at the OS level: writes are limited to the working directory plus session temp, while reads default to the entire machine; network traffic goes through a proxy allowlist that starts with zero domains. The switches live in the /sandbox panel and sandbox.enabled — there is no --sandbox flag. This post also compares sandbox runtime, dev containers, Docker, VMs, and Claude Code on the web to show when each heavier isolation tier earns its setup cost.
claude -p turns Claude Code from an interactive terminal session into a command you can embed in scripts and CI: pipe data in, get structured JSON out with --output-format json, and skip most auto-discovery with --bare. This post focuses on CLI usage, then covers the four signals that mean it's time to switch to the Python or TypeScript Agent SDK.
Claude Code connects to external tools via MCP (Model Context Protocol), with manual configuration split across three scopes: team-shared .mcp.json, personal local/user entries in ~/.claude.json, and enterprise managed config — not settings.json. This post covers claude mcp add/login flows, the transport landscape (SSE is deprecated), and tool search lazy loading.
Plugins add distribution, not new capabilities: they collect skills, agents, hooks, and MCP settings scattered across .claude/ into one manifest-backed directory that marketplaces can install, update, and version-pin. This post covers plugin structure, the minimal build flow, publishing a marketplace, and dependency version constraints.
Remote Control turns claude.ai/code or the Claude mobile app into a remote for your local Claude Code session: code still runs on your own machine, with MCP servers and local tools fully available, while transcript sync passes through Anthropic servers. This post covers startup, reconnection, push notifications, file delivery, and the security boundary.
Claude Code reads settings from five levels — managed settings, CLI flags, project local, shared project, and user — where plain values are overridden by higher levels while list keys like permissions.allow merge across scopes. This guide covers each file's role, the allow/deny/ask rule syntax, and how to verify your settings with /status and claude doctor.
A single @Claude in Slack turns a bug report into a cloud-run Claude Code session. But there are now two paths: Pro/Max stays on the original Claude Code in Slack (each session runs under an individual account), while new or migrating Team/Enterprise setups should look at Claude Tag (shared org identity, admin-configured access and spend). Check your plan before setting anything up.
Sub-agents are specialized assistants that work in their own context window: a single Markdown file defines their system prompt, tools, and model. Claude delegates automatically based on the description field, or you can @-mention to force one. This post breaks down the frontmatter schema, background execution and nested spawning, permission inheritance rules, and when not to use them.
Global skills live in ~/.claude/skills/, but they go missing in new sessions or the Desktop App? The problem usually isn't a missing file — it's that the skill descriptions aren't being loaded into context. This post clarifies the CLI vs Desktop App differences, the role of settings.json, and the most reliable fix.
Use OpenSpec to break requirements into engineering tasks, Claude Code to implement them, hooks to auto-format and protect, local review before committing, three AI reviewers running in parallel on PR, and auto-deploy after merge. This entire workflow lets one person maintain quality across six sub-projects.
Hooks are Claude Code's event system. They trigger shell commands, HTTP requests, MCP tools, or LLM evaluations automatically before/after tool execution, when a prompt is submitted, or when a task ends. Use them to block dangerous operations, run automated reviews, inject context, or write audit logs.
A Skill is an SOP written for AI. Define the steps in a Markdown file and Claude follows them. No coding required, no frameworks to learn — just write down what an experienced person would do.
Stuck mid-debug and can't fix it right now? Use /file-bug-issue to package the error analysis, reproduction steps, and attempted fixes from your conversation into a well-structured GitHub issue. Pair it with a Remote Agent to let AI automatically take over the fix.
Using Claude Code's Scheduled Remote Agent, automatically scan GitHub issues every 2 hours, implement features, open PRs, and address review feedback — no human intervention required. Humans only write issues and click merge. Pair it with the custom /publish-tasks skill to push OpenSpec engineering tasks directly to GitHub issues.
Hooks are automated safety nets (blocking bad commits), Skills are interactive workflows (running checks + auto-fixing), and instruction files (CLAUDE.md / AGENTS.md) are behavioral guidelines. Each layer operates independently, but together they enable an AI agent to automatically run lint, typecheck, and build checks before every commit.
The MCP tool was returning a description field that caused 1,033 job listings to exceed the token limit. The fix: exclude description by default and add pagination.
Claude Code has five permission modes: default (confirm each step), acceptEdits (auto-accept edits), plan (read-only planning), auto (background AI classifier review), and bypassPermissions (YOLO, skip everything). Switch with Shift+Tab or configure via settings.json. Auto mode is the sweet spot — no step-by-step confirmations, but with safety guardrails.
After finishing a debug session, just say 'write this up as a post' — Claude Code extracts content from the conversation, applies a template, generates frontmatter, and commits it to the repo. No extra writing required.
To consolidate scattered notes and showcase diverse interests, I built a personal blog using Astro + Cloudflare Workers D1, paired with a Claude post skill for zero-friction writing.