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/raisedadead/claude-code-plugins/checknpx skills add raisedadead/claude-code-plugins --skill checkgit clone --depth 1 https://github.com/raisedadead/claude-code-pluginsWhat 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 | $0.00059 | $0.02069 |
| Opus 5 | $0.00030 | $0.01035 |
| Sonnet 5 | $0.00012 | $0.00414 |
| Haiku 4.5 | $0.00006 | $0.00207 |
Grade A, and why
check 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ds:check — drift detector
Validates DOSSIER.md against reality and returns a severity-tagged violation list. It changes no DOSSIER.md content and no repo. Two derived paths are written: INDEX.md, which lib-ds-check.sh regenerates on every run (step 3), and .scratchpad/.verify-cache/, which verify_sweep.py populates at step 2a through verify_lib.cache_dir(). Both are caches rebuilt from source, never source themselves — the carve-out step 6 states.
Steps
0. Detect host env
Per ADAPTERS.md. Note Workflow tool presence (scout fan-out routing, §workflow).
1. Locate
Live dossier per ds:status step 1. --all adds archived dossiers as a sanity sweep.
2. Plan scout dispatch
One scout mission per §X repo, independent and parallel.
Mission template (per scout):
You are a dossier-scout. Read-only.
Dossier: <path-to-DOSSIER.md> (full file pasted below)
Repo to scan: <repo-path>
Headings are dual-spelled and the pasted file may use either. A ds:new
scaffold writes the plain names (`## Invariants`, `## Tasks`, `## Repos`);
older files write the sigils (`## §V`, `## §T`, `## §X`). The §-names below
are the section, not the literal heading — match whichever the file carries.
Tasks:
1. For each Invariants (§V) row with `check` = shell predicate: run the predicate, report PASS/FAIL.
2. For each Invariants (§V) row with `check` = test name: locate test in <repo-path>, run if executable, report PASS/FAIL/MISSING.
3. For each Tasks (§T) row with state=`x` + `cite=<sha>`: verify <sha> exists in <repo-path> git log. Report VALID/MISSING.
4. Refresh Repos (§X) for <repo>: git status -sb, ahead-count, latest tag, push state. Report current values; do NOT modify DOSSIER.md.
Output: caveman pipe-table. One row per finding.
<paste DOSSIER.md here>
Spawn one dossier-scout per repo, in parallel, via the Agent tool with subagent_type: dossier:dossier-scout.
§X repos > 2 and Workflow present → route the same missions through the §workflow fan-out (ADAPTERS.md): schema-validated rows, budget-gated width, crash-resumable. Otherwise the Agent spawns above.
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 · 140 lines · 59 tokens per session scan A 11500b73f204
check is a skill published in the GitHub repository raisedadead/claude-code-plugins (2 stars, last pushed 6d ago), licensed ISC. It adds 59 tokens to every session and 2,069 once invoked, about $0.0003 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…