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/gleanwork/pluginpack/pluginpack-build-and-verifynpx skills add gleanwork/pluginpack --skill pluginpack-build-and-verifygit clone --depth 1 https://github.com/gleanwork/pluginpackWhat 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 | $0.00068 | $0.00516 |
| Opus 5 | $0.00034 | $0.00258 |
| Sonnet 5 | $0.00014 | $0.00103 |
| Haiku 4.5 | $0.00007 | $0.00052 |
Grade A, and why
pluginpack-build-and-verify 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.
What it actually says
Building and verifying with pluginpack
pluginpack is a deterministic build tool. Every command is scriptable and exits non-zero on failure.
Build
pluginpack build # all configured targets
pluginpack build --target cursor # one target
pluginpack build --target claude --dry-run # print planned managed files, write nothing
Exit 0 on success; 1 on config/source/output failure. The build errors if two
targets resolve to the same output path (give them distinct outDirs).
Validate
pluginpack validate --target cursor --dir ../cursor-plugins
Checks an output directory against that target's native manifest/path/frontmatter
rules. Exit 0 = passes, 1 = errors. (For Claude, claude plugin validate is the
authoritative check; pluginpack's conformance tests use it when available.)
Diff (CI staleness gate)
pluginpack diff --target cursor --against ../cursor-plugins
Builds to a temp dir and compares managed files against an existing target repo.
Exit 1 when the repo is stale — wire this into CI to fail or to open a PR against
the generated repo. Use ignoredDiffPaths in the target config for paths the
generated repo intentionally owns.
Prune / clean
pluginpack prune --dry-run # show stale managed files
pluginpack prune # remove them
pluginpack clean --target cursor # remove all managed files for a target
These only touch files recorded in .pluginpack/<target>.json. A guard refuses
to delete anything inside your declared source (source.skills/source.plugins)
or the config; pass --force to override (rarely needed — usually it means an
outDir overlaps your source).
Developing pluginpack itself
Run the full gate before considering work done: npm run check
(format, lint, typecheck, test, build, docs). Regenerate the README CLI
reference with node dist/cli.js docs after changing commands.
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 · 61 lines · 68 tokens per session scan A 71d41b2b90ce
pluginpack-build-and-verify is a skill published in the GitHub repository gleanwork/pluginpack (5 stars, last pushed 21d ago), licensed MIT. It adds 68 tokens to every session and 516 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…