Borrowing it
Nothing to install: this file belongs to minmax/pi-cli-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/minmax/pi-cli-mcp/main/.agents/skills/validation/SKILL.mdgit clone --depth 1 https://github.com/minmax/pi-cli-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/minmax/pi-cli-mcp/validation)<a href="https://agentmods.dev/skills/minmax/pi-cli-mcp/validation"><img src="https://agentmods.dev/badge/skills/minmax/pi-cli-mcp/validation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/minmax/pi-cli-mcp/validation"><img src="https://agentmods.dev/badge/skills/minmax/pi-cli-mcp/validation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00056 | $0.00758 |
| Opus 5.5 | $0.00022 | $0.00303 |
| Sonnet 5.5 | $0.00011 | $0.00152 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
validation 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validation
Two hooks, three checks. The set is deliberately small: a hook that takes real time gets bypassed
with --no-verify, and then it does not exist.
npm run hooks # once per clone — points core.hooksPath at .githooks/
Not wired into prepare: that also runs for anyone installing this package from git, and their
hooks are not ours to configure.
pre-commit — seconds
| check | why it exists |
|---|---|
biome check . |
formatting and lint. A package.json written with spaces instead of tabs broke npm run check once. |
| lock regeneration | npm install --package-lock-only and refuse if package-lock.json moved. |
The lock check earns its place because nothing else catches it: npm ci accepts a lock that has
drifted from package.json — verified on a clean clone of a tag whose lock was two minor versions
behind. It rotted from 0.3.0 onward, bin still pointing at index.mjs long after the file was
gone, and went out inside a release tag.
When it fires, the lock has already been regenerated for you. Review it, stage it, commit again.
pre-push — the whole suite
npm test — Vitest plus the type tests. This is the run that compares our view of pi's wire
contract against the installed @earendil-works/pi-* types; see the pi-contract skill. It is the
last gate before anything leaves the machine.
Checks that were considered and dropped
Kept out on purpose, so the list stays worth reading:
| rejected | reason |
|---|---|
"no version literal in src/" |
the handshake version is read from package.json now — the duplicate cannot come back by accident |
*.tgz / stray-file guard |
one line in .gitignore does it; a hook adds nothing |
| "no orphaned processes after tests" | already asserted by child_then_answer in test/lifecycle.test.ts |
npm run build in pre-push |
compilation is covered by the type check; prepare and CI build anyway |
a separate tsc --noEmit in pre-commit |
duplicates the typecheck inside npm test |
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.
- 2mo ago First seen · 62 lines · 56 tokens per session scan A e47f2da4dd94
validation is a skill published in the GitHub repository minmax/pi-cli-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 758 once invoked, about $0.0002 per session on Opus 5.5. 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
emerging-techniques-model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
release-safety
Release safety rules. INVOKE WHEN: yarn release, npm publish, release canary, release packages, publishing, skip checks, skip tests. NEVER skip checks or tests without explicit permission.