The toolkit uses agents, skills, hooks, and scripts to absorb complexity that would otherwise fall on the user. Behavioral enforcement lives in these mechanisms, not in this file. Route to agents. The main thread is an orchestrator. It classifies requests, dispatches agents, and evaluates results. It delegates source code reading, file edits, and analysis to specialized agents. Dispatch an agent for all work. The main thread orchestrates, agents execute. Load only what you need. Context is a scarce resource. Agents…
[!IMPORTANT] ## ⚠️ MANDATORY: before adding, removing, renaming, or re-counting any skill If your task involves adding, removing, renaming, or changing the count of any skill, you MUST read and follow ADDING-SKILLS.md completely before making changes. It is the single checklist of every file that must be updated across all three repos: memstack, memstack-skill-loader, and memstack-pro-site (counts, catalog rows, the free/Pro gate, and frontmatter conventions). Skipping it causes skill-count drift and broken free/Pro gating, this is exactly how the git-guard…
Read FLYWHEEL.md first. It is how you ship a change end to end here (code → PR → green CI → [RELEASE] → PyPI → cloud → verified live) and the non-negotiable "done" bar. This file is the architecture reference; FLYWHEEL.md is the shipping loop. Never hardcode the runtime count or the runtime list anywhere new. The authoritative sources are entitlements.FREERUNTIMES | entitlements.PAIDRUNTIMES (the catalogue, and what every quoted number is derived from) and sync.FAMILYADAPTERSPECS (what the daemon actually loads…
Parent context: see the root CLAUDE.md for project-wide guidelines and behavioural rules. Chained import: @../CLAUDE.md Guidelines for the claude-md-guardian background-maintenance agent. agent/claude-md-guardian.md — installs to ~/.claude/agents/claude-md-guardian.md. Hooks use Anthropic's canonical keyed-object schema (event → array of { matcher, hooks: [{ type, command }] }): The array-of-{event, commands} shape used in earlier versions did not match the documented schema and silently did not fire. The agent uses claude-md-enhancer (the skill's frontmatter name; installed as claudeforge-skill/) as its core capability. Invoke it…
Top-level guidance for Claude Code when working on this repository. ClaudeForge is a Claude Code plugin (manifest at .claude-plugin/plugin.json) and standalone toolkit for the CLAUDE.md lifecycle: initialise, enhance, sync, and modularise files with a hard 150-line cap, automatic chaining via @path imports, and Karpathy behavioural guardrails. Works in any Claude Code or Claude.cowork project. Five components ship in this repo: Current version: 2.1.0 — see CHANGELOG.md. v1 → v2 upgrade: docs/MIGRATION_V2.md. Chained context (Claude Code auto-imports these): @skill/CLAUDE.md @command/CLAUDE.md @agent/CLAUDE.md…
Parent context: see the root CLAUDE.md for project-wide guidelines and behavioural rules. Chained import: @../CLAUDE.md Guidelines for the /enhance-claude-md and /sync-claude-md slash commands. Both install as top-level ~/.claude/commands/<name>.md so they register as /enhance-claude-md and /sync-claude-md. There is no enhance-claude-md/ bundle directory anymore — legacy bundles are backed up automatically on upgrade. command/enhance-claude-md.md Phase 3 invokes the skill by name: I can invoke the claude-md-enhancer skill directly to handle the appropriate workflow based on what I discovered above. Claude Code resolves…
Parent context: see the root CLAUDE.md for project-wide guidelines and behavioural rules. Chained import: @../CLAUDE.md Operational guidance for installers, smoke tests, and release management. Run after any change to skill/, command/, or agent/. Fresh project init: 1. mkdir test-project && cd test-project && git init && npm init -y 2. Run /enhance-claude-md. 3. Confirm generated CLAUDE.md ≤ 150 lines, contains ## Behavioral Guidelines, has tech detection right. Existing project enhance: 1. Seed CLAUDE.md with one short section. 2. Run /enhance-claude-md;…
Parent context: see the root CLAUDE.md for project-wide guidelines and behavioural rules. Chained import: @../CLAUDE.md Guidelines for the claudeforge-skill Python modules and the karpathy-guidelines skill. Five modules live under skill/: Every generated CLAUDE.md must contain: calculatequalityscore() breakdown: skill/workflow.py → detecttech_stack() reads these signals: Add new detectors there, not in the template selector. skill/karpathy-guidelines/SKILL.md is the standalone skill installed at ~/.claude/skills/karpathy-guidelines/. Adapted with attribution from the MIT-licensed [forrestchang/andrej-karpathy-skills](https://github.com/forrestchan
The CLAUDE.md file is Anthropics way of giving Claude Code knowledge about your repository that it can carry across sessions. If you or your team uses multiple coding agents eithe…
Use the /browse skill from gstack for all web browsing. Never use mcpclaude-in-chrome* tools. Available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /design-shotgun, /design-html, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse, /connect-chrome, /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /retro, /investigate, /document-release, /codex, /cso, /autoplan, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade, /learn When the user's request matches an available skill, ALWAYS invoke it using the Skill tool as your FIRST action. Do NOT answer directly, do NOT use other tools first. The skill has specialized…
Nelson is a Claude Code skill for coordinating agent work using Royal Navy terminology. It provides an eight-step operational framework: Sailing Orders, The Estimate, Battle Plan, Form the Squadron, Get Permission to Sail, Quarterdeck Rhythm, Action Stations, and Stand Down. This repo has automated sensors that you (the agent) should run and read carefully before considering a task done. They're how the codebase gives you fast feedback about whether your changes are maintainable. - Linter — ruff check. Config in…
This is a content repository, not an application. It publishes a Claude Code plugin — a collection of 22 SKILL.md files (in skills/<NN-skill-name>/) that teach Claude domain-specific cybersecurity methodology (recon, vuln scanning, exploit dev, RE, malware analysis, threat hunting, IR, network/web/cloud security, SOC automation, log analysis, crypto, red/blue team ops, AI/LLM security, mobile, OT/ICS, GRC, supply chain security, threat intelligence/CTI, purple team/adversary emulation). Each skill directory optionally ships standalone Python automation scripts and example usage docs that the SKILL.md references.
The adversarial eval suite defines the product. Start there. Before implementation, encode behavioral changes in evals/adversarial-evals.json and leave legacy evals/evals.json untouched because it serves old consumers, not current product decisions.
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
notqueCLAUDE.md
