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/musingfox/cc-plugins/specnpx skills add musingfox/cc-plugins --skill specgit clone --depth 1 https://github.com/musingfox/cc-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 | $0.00081 | $0.01542 |
| Opus 5 | $0.00041 | $0.00771 |
| Sonnet 5 | $0.00016 | $0.00308 |
| Haiku 4.5 | $0.00008 | $0.00154 |
Grade A, and why
spec 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Spec Library
A spec entry answers what must not change. An ADR answers why we chose this. Same directory convention, same status vocabulary, different lifespan: an ADR is history the moment it is accepted; a spec is load-bearing until it is superseded.
Do NOT use for: describing what the system currently looks like. That is the code's job, and a spec that restates it becomes a drift source the first time someone edits without updating the entry.
Directory
Scan docs/spec/. If it does not exist and the user wants an entry, ask where
it should live. Override with SPEC_DIR.
What earns an entry
A rule belongs here only if its violation is silent. The entries already in
this repo all close by naming that silence: a vendored copy drifts while both
copies still run; rc=0 proves the process did not crash, not that the work is
done; Edit turns a FAIL into a PASS and the deliverable still looks like the
deliverable.
Anything that fails loudly needs no entry — the compiler catches it, or a test goes red. If you cannot write the sentence explaining why nobody would notice the violation, the rule probably does not belong in the library.
Entry format
One entry per file, named <id>.md. The id is kebab-case and shows up as the
heading of every slice, so make it readable:
---
id: judge-seats-cannot-edit
status: accepted # proposed | accepted | superseded
scope: # file globs, never module names
- "pi-dispatch/agents/reviewer.md"
verify: check:<shell command that exits 0 when the spec holds>
related: [other-spec-id] # entries this one bears on
source: null # where it came from — milestone slug, or null
adr: null # link when superseded
---
source is the birth record. An entry has two birthplaces: a milestone
settles and names an interface later flows must honour, or a flow finishes and
main finds an invariant the run revealed. Either way, write down which — a rule
whose origin nobody remembers is a rule nobody dares delete, and that is how a
spec library silts up into a layer of untouchable sediment.
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 · 147 lines · 81 tokens per session scan A 88fdfdec735f
spec is a skill published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 1,542 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…