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/ericfitz/skills/docsnpx skills add ericfitz/skills --skill docsgit clone --depth 1 https://github.com/ericfitz/skillsWhat 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 | $0.00071 | $0.01150 |
| Opus 5 | $0.00036 | $0.00575 |
| Sonnet 5 | $0.00014 | $0.00230 |
| Haiku 4.5 | $0.00007 | $0.00115 |
Grade A, and why
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 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs
Read what this project wrote down about itself, and extract what it says the system is supposed to do.
This is the second gate phase: journeys, topology, and other consumers all read from
the record this phase produces, so they read it once and agree about it.
Reference: ${CLAUDE_PLUGIN_ROOT}/references/doc-sources.md
Contract: ${CLAUDE_PLUGIN_ROOT}/references/contracts/docs.schema.json
Example: ${CLAUDE_PLUGIN_ROOT}/references/contracts/examples/docs.example.json
Usage
/profile:docs [path]
Input
You are normally handed a profile:stack contract; use inventory.docs and
inventory.docs_sites as your in-repo census. You may also be handed external
document pointers — URLs, wiki locations, local paths.
Standalone invocation: if you were not handed a stack contract, invoke
profile:stack first and use its output. If you were not given external pointers and
you are running in a conversation with the user, ask once whether any requirements
documents, PRDs, or specifications live outside the repository, and accept "none".
Procedure
-
Resolve sources. For each in-repo document, the capability is Read. For each external pointer, match it to a capability that is already available in this session per the source-tier table. Record every resolved source in
sources_available[]with the capability you used. -
Record what you cannot reach. A pointer with no matching capability goes in
unavailable_sources[]with a reason and asuggested_remedydrawn from the remedy table. Then continue — an unreachable source is a reported gap, never a stop. -
Census. For every candidate, record locator, title, headings, and
last_modified. Correct the inventory'sdoc_type_guess, which is a path-based guess made without reading anything. -
Rank by the signals in the reference, in the order given.
-
Deep-read down the ranking to the 25-document budget. Each document read becomes a
corpus[]entry withread: fullorread: skimmedand anauthorityvalue. Everything below the line becomes adeferred[]entry.
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 · 96 lines · 71 tokens per session scan A aaba6d895f7e
docs is a skill published in the GitHub repository ericfitz/skills (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,150 once invoked, about $0.0004 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…