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/lestrrat-ai/claude-code-plugins/compile-apinpx skills add lestrrat-ai/claude-code-plugins --skill compile-apigit clone --depth 1 https://github.com/lestrrat-ai/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 | $0.00058 | $0.00683 |
| Opus 5 | $0.00029 | $0.00342 |
| Sonnet 5 | $0.00012 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
compile-api 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 2d ago.
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.
What it actually says
Compile Fusion API Database
Invocation: Claude Code /fusion:compile-api; Codex $fusion:compile-api.
-
Resolve
scripts/compile_fusion_api.pyfrom this activeSKILL.mdto an absolute path. NEVER use a plugin-root environment variable. -
Run:
["python3", "<absolute-compile_fusion_api.py>"]Needs network access to
api.github.com(commit and file listing) andraw.githubusercontent.com(the stub files themselves), and to no other host:github.comis only the source string recorded in the database. The default output is the user cache (~/.cache/fusion-api-db/fusion-api.db), whichquery-apiprefers over the database bundled with the plugin — a recompile takes effect immediately, no plugin reinstall. -
Options, only when the user asks for them:
--ref <git-ref>compiles a specific ref of the reference repo (defaultmain).--source <dir>parses a local directory ofadsk/*.pystubs instead of downloading. It resolves no ref, so the two options are refused together (usage error, exit 2) rather than--refbeing ignored; a user asking for both wants a download of that ref.--output <path>writes elsewhere. Refreshing the plugin's bundled copy (authoring checkout of this plugin only) →--output <plugin>/skills/query-api/data/fusion-api.db, then commit the result.
-
Report the script's final line on stdout (path, symbol count, member count) and the
compiling <source>@<commit>line stderr opens with, as the source record. Every path emits that line: a download names the reference repo, the resolved commit, and the ref that was requested (compiling <repo>@<sha> (requested ref '<ref>')), a--sourcecompile names the local directory andlocalin place of a commit. Report the requested ref as well as the commit — the resolved commit alone cannot be checked against the ref the user named. Relay everywarning:line on stderr too: one kind reports how many statements used a construct the compiler does not index, and one kind reports a warning Python raised while parsing a named stub. Non-zero exit → relay stderr as-is and stop.
The script rebuilds the whole database from scratch; there is no incremental mode. It compiles into a staging file next to the output and replaces the output only after every stub has parsed and the result has been checked to be non-empty, so a compile that fails partway leaves the existing database in place. A compile that succeeds still discards the previous contents — anything hand-edited into that database is lost.
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.
- 2d ago First seen · 45 lines · 58 tokens per session scan A 74f451f8f575
compile-api is a skill published in the GitHub repository lestrrat-ai/claude-code-plugins (18 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 683 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 2026-08-30.
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…