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/patternfly/patternfly-mcp/add-docs-linksnpx skills add patternfly/patternfly-mcp --skill add-docs-linksgit clone --depth 1 https://github.com/patternfly/patternfly-mcpWhat 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 | $0.00074 | $0.01055 |
| Opus 5 | $0.00037 | $0.00528 |
| Sonnet 5 | $0.00015 | $0.00211 |
| Haiku 4.5 | $0.00007 | $0.00105 |
Grade A, and why
add-docs-links scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Response must be 2xx (e.g. `curl -sI -o /dev/null -w "%{http_code}" "<url>"`). If not, fix ref or path; do not add a dead link. How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Documentation Links to docs.json
When to use
- User wants to add, change, or remove rows in
src/docs.json, or fix broken / unreachable catalog links - User provides a GitHub URL (blob or raw) to register in the catalog — convert blob → raw, pick refs, verify reachability, shape entries, update
metaandgenerated, and run tests - User asks to update or fix
docs.jsonentries, contribute to the docs catalog, or align with docs.json tests and CI audit
For edits or removals: find the row by path and/or its docs key; update meta / generated; run tests. Same rules as adds: whitelist, unique path, and src/__tests__/docs.json.test.ts (including baseHashes and the Repository Breakdown table when refs change).
Workflow
-
Resolve raw URL and ref
- Map the link to
owner/repoand file path; build rawhttps://raw.githubusercontent.com/{owner}/{repo}/{ref}/{file}. - Prefer the same
refalready used indocs.jsonfor thatpatternfly/<repo>(copy from an existingpath). - New
patternfly/<repo>(or new ref /rh-uxd/<repo>): after you add URLs, opendocs.json.test.tsand updateexpect(baseHashes.size)and the Repository Breakdown table (including the Total row)—do not guess counts from this skill. - New ref for an existing repo: resolve SHA (e.g. commits API) or use a stable tag.
- Map the link to
-
Whitelist
pathmust matchwhitelist.urlsinsrc/options.defaults.ts. See reference.md — URL whitelist. Use https only. Do not widen the whitelist in a catalog-only PR.
-
Reachability
- Response must be 2xx (e.g.
curl -sI -o /dev/null -w "%{http_code}" "<url>"). If not, fix ref or path; do not add a dead link.
- Response must be 2xx (e.g.
-
Unique
path- Each
pathappears once in the whole file.
- Each
-
Placement in
docs- New top-level key under
docs(e.g."AiHelpers"): append as the last property inside"docs": { … }(after the current last key’s block). Do not insert mid-file by theme or alphabet. - New object in an existing key’s array: append to the end of that array unless the user specifies order.
- Edits: keep the same key and array index unless the user asks to move.
- New top-level key under
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 · 65 lines · 74 tokens per session scan A ced839009b53
add-docs-links is a skill published in the GitHub repository patternfly/patternfly-mcp (3 stars, last pushed 6d ago), licensed MIT. It adds 74 tokens to every session and 1,055 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…