You are a technical analyst. Your job is to scan the project codebase and produce accurate, project-specific documentation used by all downstream agents.
context-mode (mksglu/context-mode) — routes large outputs through a sandbox to protect the context window
If both are present, use them in Steps 3–4 as described below. If either or both are missing, proceed with the native fallback approach: use find, grep, cat, and git commands directly, routing large outputs through ctx_execute / ctx_execute_file if context-mode is available, otherwise summarise inline.
Use understand-anything to analyse the entire codebase. If context-mode is available (verified in Step 1), route ALL output through its tools (ctx_batch_execute / ctx_execute_file) — never dump raw file contents into the main context window. If context-mode is not available, summarise each file’s findings inline and avoid printing raw file contents.
Produce .claude/pipeline/project-doc.md using the following structure (based on the architecture-blueprint-generator pattern):
md
# Project Documentation> Generated: [timestamp] | Mode: FULL## Tech Stack- Runtime: [e.g. Node.js 20, Python 3.11]- Language: [e.g. TypeScript, Python]- Framework: [e.g. Next.js 14 App Router, FastAPI]- Database: [e.g. PostgreSQL via Prisma]- Styling: [e.g. Tailwind CSS]- State Management: [e.g. Zustand, Redux]## Dependencies[Key libraries with versions, grouped by: core / dev / testing]## Architecture Pattern[e.g. Feature-based, Layered MVC, Clean Architecture][Describe how the project is structured and why]## Folder Structure[Top-level directory map with purpose of each folder]## Code Style Conventions[Naming patterns, file naming, import ordering, export patterns][Inferred from actual code — not guessed]## Modularity Practices[How concerns are separated, shared module locations, service patterns]## Data Architecture[Entity relationships, data access patterns, ORM usage]## Cross-Cutting Concerns[Auth/authz approach, error handling patterns, logging, validation]## Service Communication[REST / GraphQL / event-driven — document what actually exists]## Test Coverage- Overall coverage: [X%]- Testing framework: [e.g. Jest, Vitest, Pytest]- Key untested areas: [list]- Test patterns used: [unit / integration / e2e]## Entry Points[Main files, key config files, environment setup]## Changed Files[Only present in delta scans — list of files re-scanned]## Last Scanned[ISO timestamp]
After writing project-doc.md, proceed to Step 4 to generate AGENTS.md.
Run git diff HEAD~1 --name-only to get changed files
If no changed files, report “No changes detected — project-doc.md is current” and exit
Use understand-anything to re-analyse only the changed files; route output through ctx_execute_file if context-mode is available, otherwise summarise inline
Patch only the affected sections of .claude/pipeline/project-doc.md
Update the Last Scanned and Changed Files fields
Proceed to Step 4B (architectural change detection)
Write AGENTS.md to the repo root. This is NOT a copy of project-doc.md — it is rewritten as agent instructions, tailored to this specific project. Every agent reads this file first.
Structure:
md
# AGENTS.md — [Project Name]> Auto-generated by the dev pipeline scanner. Do not edit manually.> Last updated: [timestamp]> ⚠️ To update this file, architectural changes must be detected by the scanner and confirmed by a human.## How to Read This FileEvery agent in this pipeline reads this file before doing any work.It defines the rules, patterns, and guardrails specific to this project.## Stack Context[One-line summary: e.g. "Next.js 14 App Router + Prisma + PostgreSQL + Tailwind + Vitest"]## Code Style Rules[Written as DO/DON'T instructions inferred from actual codebase patterns]Example:- DO use named exports. Default exports are not used in this project.- DON'T add business logic to API route handlers — delegate to /lib/services/- DO use [naming convention] for [file type]## Architecture Guardrails[Rules derived from the actual architecture — not generic advice]Example:- This project uses the Repository pattern. Never query the DB directly from components.- All API responses must go through the [ResponseWrapper] utility.## Testing Requirements[Coverage stat + specific rules for this project]Example:- Current coverage: 67%. All new code must include unit tests.- QA agent: flag any feature with <80% coverage on new code.- Integration tests use [real DB / mock DB] — do not change this.## Modularity Conventions[Specific rules about where code goes]Example:- Shared UI components → /components/ui- Business logic → /lib/services/[domain]/- Types → /types/[domain].ts## Security Rules (All Agents)- Never hardcode secrets, tokens, or credentials- Use environment variables for all sensitive config- Flag any auth-adjacent code changes immediately## Agent-Specific Instructions### Orchestrator[Project-specific questions to always ask — e.g. "Does this touch the payment flow?"]### Architect[Known complexity areas, performance constraints, patterns to prefer][e.g. "This project has a known N+1 issue in /lib/services/orders — avoid adding more eager loading"]### Developer[Specific libraries to use, anti-patterns banned in this codebase][e.g. "Use dayjs — moment is banned", "Use React Query for all data fetching — no raw fetch()"]### PR Reviewer[What counts as 🔴 Critical vs 🟡 Should Fix in this project][e.g. "Any change to /lib/auth/ is automatically 🔴 Critical — requires human approval"]### QA Agent[Known edge cases for this domain, critical user paths to always test][e.g. "Always test empty state, loading state, and error state for every UI feature"]
If the project is MERN stack (MongoDB + Express + React + Node.js — detected from package.json / requirements), append a ### MERN Stack Notes section to AGENTS.md covering: use Mongoose middleware over raw queries, handle async errors in Express with a central error handler, avoid storing JWT tokens in localStorage (use httpOnly cookies), and never expose Mongoose error objects directly in API responses.
After patching project-doc.md, compare the new version against the previous. Check for:
New framework or major library added
New architectural directory pattern created (e.g. new /lib/hooks/, /services/)
Major dependency swap (e.g. axios → fetch, moment → dayjs)
New auth or session handling pattern
If any detected, show:
⚠️ Architectural change detected in delta scan: [List specific changes found]AGENTS.md may need updating. Review and confirm: [y] Update AGENTS.md — patch affected sections only [n] Skip — this is not an architectural change
Only on [y] confirmation: patch the relevant sections of AGENTS.md. Never rewrite the full file.
Update state.json field checkpoints.scan = "completed".
About this skill
Trigger
Scans the codebase to generate project-doc.md and AGENTS.md. Use when bootstrapping a new agent-driven repo, refreshing project documentation after architectural changes, or running a delta scan to detect drift. Runs a full scan on first use and a smart delta scan on subsequent runs. Uses understand-anything + context-mode when available, falls back to native tools otherwise. Only updates AGENTS.md on detected architectural changes with human confirmation.
The verbatim description from this skill’s front matter — the string an agent matches on to decide whether to load it.
MIT — the text of every skill is reproduced unmodified, frontmatter included, under the upstream licence.
Discovery
183 skills found by walking the repository tree for SKILL.md, not by matching a directory convention. 51 distinct layouts observed: plugins/accessibility-compliance/skills/*/SKILL.md, plugins/agent-teams/skills/*/SKILL.md, plugins/api-scaffolding/skills/*/SKILL.md, plugins/avoid-ai-writing/skills/*/SKILL.md, plugins/backend-development/skills/*/SKILL.md, plugins/before-you-build/skills/*/SKILL.md, plugins/block-no-verify/skills/*/SKILL.md, plugins/blockchain-web3/skills/*/SKILL.md, plugins/brand-landingpage/skills/*/SKILL.md, plugins/business-analytics/skills/*/SKILL.md, plugins/cicd-automation/skills/*/SKILL.md, plugins/cloud-infrastructure/skills/*/SKILL.md, plugins/conductor/skills/*/SKILL.md, plugins/data-engineering/skills/*/SKILL.md, plugins/database-design/skills/*/SKILL.md, plugins/developer-essentials/skills/*/SKILL.md, plugins/dgx-spark-ops/skills/*/SKILL.md, plugins/documentation-generation/skills/*/SKILL.md, plugins/documentation-standards/skills/*/SKILL.md, plugins/dotnet-contribution/skills/*/SKILL.md, plugins/file-conversion/skills/*/SKILL.md, plugins/framework-migration/skills/*/SKILL.md, plugins/frontend-mobile-development/skills/*/SKILL.md, plugins/game-development/skills/*/SKILL.md, plugins/hermes-tweet/skills/*/SKILL.md, plugins/hr-legal-compliance/skills/*/SKILL.md, plugins/incident-response/skills/*/SKILL.md, plugins/javascript-typescript/skills/*/SKILL.md, plugins/kubernetes-operations/skills/*/SKILL.md, plugins/llm-application-dev/skills/*/SKILL.md, plugins/llm-finetuning/skills/*/SKILL.md, plugins/machine-learning-ops/skills/*/SKILL.md, plugins/observability-monitoring/skills/*/SKILL.md, plugins/payment-processing/skills/*/SKILL.md, plugins/plugin-eval/skills/*/SKILL.md, plugins/pptx-deck-creation/skills/*/SKILL.md, plugins/protect-mcp/skills/*/SKILL.md, plugins/python-development/skills/*/SKILL.md, plugins/quantitative-trading/skills/*/SKILL.md, plugins/reverse-engineering/skills/*/SKILL.md, plugins/review-agent-governance/skills/*/SKILL.md, plugins/security-scanning/skills/*/SKILL.md, plugins/shell-scripting/skills/*/SKILL.md, plugins/ship-mate/skills/*/SKILL.md, plugins/signed-audit-trails/skills/*/SKILL.md, plugins/skill-forge-essentials/skills/*/SKILL.md, plugins/social-publishing/skills/*/SKILL.md, plugins/startup-business-analyst/skills/*/SKILL.md, plugins/superself/skills/*/SKILL.md, plugins/systems-programming/skills/*/SKILL.md, plugins/ui-design/skills/*/SKILL.md.
Issue colours
Resolved from a deterministic hash of the owner name. Two accent tones are generated per issue and each is proven against its own ground before it ships: a single accent that passes AA on both light and dark paper is arithmetically impossible.
Heading repairs
1 repair applied to this skill so the document has one h1 and no skipped levels:
Shifted “8 headings” from h1 to h2 so the skill title is the only h1.
Images inside a skill come from the upstream repository. Where the author gave no alternative text we mark the image decorative rather than inventing a description — a plausible caption we made up is worse than none for the reader who depends on it.
Marketplace
A plugin manifest is published at .claude-plugin/marketplace.json by Seth Hobson, declaring 94 plugins. It is read for editorial metadata only — never as the skill index, which is always the repository tree.
Signal
Install counts come from skills.sh. They measure downloads, not quality, and an unranked repository is not an unread one.
Agent surfaces
The whole issue is available as one markdown document at /wshobson/agents.md, and each skill at its own .md URL.
Publication
Set by Skills Docs from the source repository. Body text is Literata at the reader’s chosen size and measure; code is Geist Mono. Nothing on this page was written by us except this paragraph.