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/qa-vault/codelore/document-featurenpx skills add qa-vault/codelore --skill document-featuregit clone --depth 1 https://github.com/qa-vault/codeloreWhat 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 | $0.00159 | $0.02891 |
| Opus 5 | $0.00079 | $0.01445 |
| Sonnet 5 | $0.00032 | $0.00578 |
| Haiku 4.5 | $0.00016 | $0.00289 |
Grade A, and why
document-feature 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 yesterday.
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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Documentation Skill
Create and maintain reference documentation for implemented features and functionality. Each document answers the questions a developer (human or AI) would ask before touching the code: What does this do? Why was it done this way? What are the gotchas?
This is NOT a changelog or session log. It doesn't track when things happened or who did them. It describes how things work right now and why.
What Makes a Good Implementation Doc
Think of it like a briefing document. An AI agent picks up a task that says "add rate limiting to the auth endpoints." Before writing a line of code, it reads the auth implementation doc and learns: the auth module uses JWT with symmetric HS256, tokens are verified via middleware on each request, the token store is in-memory (no Redis yet), and the original design chose simplicity over horizontal scalability. Now the agent can make an informed decision about where and how to add rate limiting without breaking assumptions.
A good implementation doc has these qualities:
- Self-contained. A reader with zero prior context can understand the feature.
- Honest about trade-offs. Documents what was chosen AND what was sacrificed.
- Actionable. Contains enough detail that someone can modify the feature safely.
- Current. Reflects the code as it exists right now, not a historical record.
- Concise. Covers what matters, skips what doesn't. No padding.
Step 0: Discover Existing Documentation
Before writing anything, scan the project for existing docs. The goal is consistency — new documents should look like they belong.
Discovery Procedure
-
Find the docs directory. Look for
docs/,doc/,documentation/, or docs at the project root. CheckREADME.mdfor links to documentation. If nothing exists, ask the user where docs should live. -
Study existing docs. If implementation docs already exist, open 2–3 of them and extract the conventions:
- File naming pattern (kebab-case? UPPERCASE? numbered?)
- Document structure (what sections do they use? what order?)
- Frontmatter (YAML? which fields?)
- Formatting style (prose vs bullets, heading levels, code reference style)
- Level of detail (high-level overviews vs deep implementation details?)
- How they cross-reference other docs or code
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.
- yesterday First seen · 265 lines · 159 tokens per session scan A c50c1fa4259d
document-feature is a skill published in the GitHub repository qa-vault/codelore (2 stars, last pushed 4mo ago), licensed MIT. It adds 159 tokens to every session and 2,891 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 2026-08-31.
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…