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/minmax/pi-cli-mcp/releasenpx skills add minmax/pi-cli-mcp --skill releasegit clone --depth 1 https://github.com/minmax/pi-cli-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 | $0.00052 | $0.00876 |
| Opus 5 | $0.00026 | $0.00438 |
| Sonnet 5 | $0.00010 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
release 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Releasing pi-cli-mcp
Publishing happens in CI, triggered by a tag. npm publish from a workstation works but produces a
package without provenance — 0.4.0 went out that way and has dist.attestations: null, while
0.5.0 went through the tag and carries a SLSA attestation. Use the tag.
The sequence
Move the Unreleased entries in CHANGELOG.md under the new version with
its date first — after the tag is pushed the publish has already happened and the entry is being
written from memory.
npm version <new-version> --no-git-tag-version # updates package.json AND package-lock.json
npm run check # format, types, full suite
git add package.json package-lock.json CHANGELOG.md
git commit
git tag -a vX.Y.Z -m "<what changed in behaviour>"
git push origin main
git push origin vX.Y.Z # this is what publishes
Then confirm, on the registry rather than on trust:
gh run watch $(gh run list --limit 1 --json databaseId --jq '.[0].databaseId') --exit-status
npm view pi-cli-mcp version
npm view pi-cli-mcp --json | python3 -c "import json,sys; print(json.load(sys.stdin)['dist'].get('attestations'))"
attestations: null means the tag path was bypassed.
Choosing the number
Pre-1.0, so nothing is strictly forced, but keep the signal honest: a changed default is a
behaviour change even when the API is identical. Making rpc the default transport went out as
0.5.0, not 0.4.1, so that anyone reading the number sees it.
What has actually gone wrong here
npm versionvs hand-editing. Bumping the version by editingpackage.jsondirectly leavespackage-lock.jsonbehind. That lock sat on0.3.0— with abinpath that stopped existing at the TypeScript migration — and shipped inside tagv0.5.0that way.npm ciaccepts such a lock without complaint, so CI will not tell you. The pre-commit hook now will; see thevalidationskill.- A second copy of the version.
SERVER_INFOused to hard-code it, and the copy clients see in the MCP handshake was a release behind. It is read frompackage.jsonnow — do not reintroduce a literal. - Push
maintoo. Only the tag is needed to publish, but ifmainlags, the README people read describes different behaviour from the package they installed.
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 · 75 lines · 52 tokens per session scan A a4a5528ac0be
release is a skill published in the GitHub repository minmax/pi-cli-mcp (0 stars, last pushed 9d ago), licensed MIT. It adds 52 tokens to every session and 876 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…