Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/espennilsen/pi/codebase-docsnpx skills add espennilsen/pi --skill codebase-docsgit clone --depth 1 https://github.com/espennilsen/piWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00158 | $0.01589 |
| Opus 5 | $0.00079 | $0.00794 |
| Sonnet 5 | $0.00032 | $0.00318 |
| Haiku 4.5 | $0.00016 | $0.00159 |
Grade A, and why
codebase-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Documentation Skill
Generate and maintain a structured set of markdown files in docs/ that give AI agents (and humans) a fast, accurate understanding of a codebase without needing to search through source files.
Philosophy
The docs you produce are a map, not the territory. They should let an AI agent answer questions like "where does authentication happen?", "how does data flow from API to database?", or "what are the key abstractions?" — without reading every file. Optimize for navigability and accuracy over exhaustiveness.
When to Use This Skill
- User asks to document a codebase or project
- User wants to update existing docs after making changes
- User wants AI-friendly project documentation
- User mentions
docs/directory maintenance - User wants architecture or structural documentation
Step 1: Assess the Codebase
Before writing anything, understand what you're documenting.
- Read the project root — check for existing README, package.json/Cargo.toml/pyproject.toml, config files, and any existing
docs/directory - Map the directory structure — identify source directories, test directories, config, scripts, assets
- Identify the tech stack — languages, frameworks, key dependencies, build tools
- Find entry points — main files, route definitions, CLI entry points, exported modules
- Detect patterns — architecture style (MVC, microservices, monolith, plugin-based), state management, data layer
If a docs/ directory already exists, read it first. You'll be updating, not starting from scratch.
Step 2: Generate the Documentation Set
Create the docs/ directory with the files described below. Not every project needs every file — use judgment. A small CLI tool doesn't need DATA_MODEL.md, and a pure library doesn't need DEPLOYMENT.md.
Refer to references/doc-templates.md for the exact templates and structure for each file. Read that file before writing any documentation.
Required Files (always generate)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 126 lines · 158 tokens per session scan A 00e64dc42f3a
codebase-docs is a skill published in the GitHub repository espennilsen/pi (117 stars, last pushed 9d ago), licensed MIT. It adds 158 tokens to every session and 1,589 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…