codebase-context-generator SKILL.md skillA

codebase-context-generator from larchanka/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add larchanka/skills/codebase-context-generator@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
larchanka/skills
Path
codebase-context-generator/SKILL.md
Versions recorded
1
Latest version
v1.0.0, committed Oct 25, 2026
Size
8,558 bytes
Repository stars
50
License
MIT

Generates comprehensive AI context, AGENTS.md, and structured documentation in a context/ directory for any brownfield codebase using Tree-sitter AST extraction, dependency analysis, predefined python scripts, and orchestrated subagents.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Codebase Context Generator

This skill transforms any brownfield or non-AI-adapted codebase into an AI-ready repository. It generates:
1. **`AGENTS.md`**: The primary operational instruction manual for AI agents operating in the repository.
2. **`context/`**: A structured documentation directory detailing architecture, modules, dependencies, and engineering conventions.

The skill combines deterministic Tree-sitter AST parsing via predefined Python scripts with semantic multi-agent synthesis to produce accurate, information-dense documentation without blowing token budgets.

```mermaid
flowchart TD
    TargetRepo["Target Codebase"] --> Phase1["Phase 1: Deterministic AST & Graph Extraction<br/>(ast_scanner.py, dependency_graph.py, symbol_graph.py)"]
    Phase1 --> Cache[".context_cache/<br/>ast_manifest.json, dependency_graph.json, symbol_graph.json"]
    Phase1 --> SigDoc["context/signatures.md<br/>(Full function signatures & argument types)"]
    
    Cache --> Phase2["Phase 2: Environment & Commands Discovery<br/>(Subagent: repo-inspector)"]
    Cache --> Phase3["Phase 3: Domain & Architecture Analysis<br/>(Subagent: domain-architect)"]
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add larchanka/skills/codebase-context-generator@sha256:024fe3a7bd1a5d39

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_jyvmlg5mzgjovsbu.svg)](https://markdownregistry.com/a/art_jyvmlg5mzgjovsbu)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 25, 2026.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-10-25 5ff04b8 8,558 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8558 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

larchanka/skills · 50 stars · license MIT · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_jyvmlg5mzgjovsbu
GET https://markdownregistry.com/api/v1/resolve?ref=larchanka/skills/codebase-context-generator
GET https://markdownregistry.com/api/v1/blob/024fe3a7bd1a5d3906a9a3870b8f9bb61b8ff7edb9bed145d88ccfc52b92748d

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from larchanka/skills

agent-loop SKILL.md skill
larchanka/skills · agent-loop/SKILL.md · Orchestrates a multi-agent loop involving planning, development, review, and publishing sub-agents to implement and…
v1.3.0 · audit A · 50 stars
code-review SKILL.md skill
larchanka/skills · code-review/SKILL.md · Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another…
v1.1.0 · audit A · 50 stars
email-triage SKILL.md skill
larchanka/skills · email-triage/SKILL.md · Autonomous multi-agent email triage system powered by Google Workspace CLI (gog). Discovers accounts dynamically…
v1.0.0 · audit A · 50 stars
manual-automation SKILL.md skill
larchanka/skills · manual-automation/SKILL.md · Manual browser testing and automation using Chrome DevTools MCP server. Handles port management, app launch, browser…
v1.0.0 · audit A · 50 stars
planning-and-task-breakdown SKILL.md skill
larchanka/skills · planning-and-task-breakdown/SKILL.md · Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into…
v1.1.0 · audit A · 50 stars
project-change-intelligence SKILL.md skill
larchanka/skills · project-change-intelligence/SKILL.md · Progressively investigate PRs, commits, releases, and project evolution. Start with a lightweight assessment…
v1.0.0 · audit A · 50 stars
pull-request SKILL.md skill
larchanka/skills · pull-request/SKILL.md · Creates a new feature branch from current git changes, commits them, pushes to the remote, and opens a github pull…
v1.1.0 · audit A · 50 stars
refactoring SKILL.md skill
larchanka/skills · refactoring/SKILL.md · Executes the 'Then Make it Right' discipline: pins behavior, eliminates duplication, enforces CRAP < 10, runs mutation…
v1.0.0 · audit A · 50 stars
slack-cli SKILL.md skill
larchanka/skills · slack-cli/SKILL.md · Interact with Slack workspaces safely via dedicated Python helper scripts. Allows reading unread messages, channels…
v1.0.0 · audit B · 50 stars
test-driven-development SKILL.md skill
larchanka/skills · test-driven-development/SKILL.md · Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions…
v1.1.0 · audit A · 50 stars
yt-random-comment-picker SKILL.md skill
larchanka/skills · yt-random-comment-picker/SKILL.md · Downloads YouTube video comments, filters to unique authors, and randomly selects one comment to return.
v1.0.0 · audit A · 50 stars

Every file in larchanka/skills

Browse by kind, by grade A, or by owner.