pi-cli-mcp: Skill for Claude Code

.agents/skills/testing/SKILL.md

testing is a skill for Claude Code, Codex from minmax/pi-cli-mcp. It costs 62 tokens per session (953 once invoked), scanned A, original, MIT.

Instructions for testing pi-cli-mcp through its real standard-input and standard-output server protocol, using a fake pi program instead of replacing the server’s own code.

In plain words
What is it for?
Use it when adding or debugging tests, creating test scenarios, checking one test file, or investigating tests that fail only in a full run.
Why use it?
This checks the actual communication path and helps expose failures involving sessions, cancellation, timeouts, errors, and unfinished processes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is minmax/pi-cli-mcp's own configuration. It tells Claude Code and Codex how to work on pi-cli-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pi-cli-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/minmax/pi-cli-mcp/main/.agents/skills/testing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/minmax/pi-cli-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/minmax/pi-cli-mcp/testing/github.svg)](https://agentmods.dev/skills/minmax/pi-cli-mcp/testing)
Your own site
<a href="https://agentmods.dev/skills/minmax/pi-cli-mcp/testing"><img src="https://agentmods.dev/badge/skills/minmax/pi-cli-mcp/testing/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.

agentmods 80×15 button for testing

Your own site · 80×15
<a href="https://agentmods.dev/skills/minmax/pi-cli-mcp/testing"><img src="https://agentmods.dev/badge/skills/minmax/pi-cli-mcp/testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 953 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.00953
Opus 5.5 $0.00025 $0.00381
Sonnet 5.5 $0.00012 $0.00191
Haiku 4.5 $0.00006 $0.00095

Measured 2mo ago against content hash 7a7d3e0fb4b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

testing 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.

.agents/skills/testing/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Testing

The suite drives the real server over stdio and points it at a fake pi binary. No mocks of our own code: a test that passes against a stub of runPi would prove nothing about the protocol.

npm test                      # suite + type tests, no API access, no tokens
PI_CLI_MCP_LIVE=1 npm test    # also runs the real pi binary
npx vitest run test/x.test.ts # one file

Tests run the server from src/ through Node's TypeScript support, so they exercise the source, not a stale dist/.

Layout

file covers
protocol.test.ts handshake, JSON-RPC conformance, notifications, frame limits
answer.test.ts answer selection, stop-reason handling, stats line, input validation
failure.test.ts what a killed run reports: session id, progress, resumability, stderr scrubbing
lifecycle.test.ts timeout, cancellation, shutdown, concurrency, leftover-process cleanup
sessions.test.ts continuity across restarts, remembered options, the session mutex
transport.test.ts print vs rpc, and reaching a running turn
packaging.test.ts zero runtime dependencies, publishable file list
pi-contract.test-d.ts types against the installed pi — see the pi-contract skill
live.test.ts the real pi, opt-in

The fake pi

test/fixtures/fake-pi.mjs emits a pi-shaped --mode json stream and speaks the rpc command protocol. It exists for the paths a live model will not produce on demand: a bad or unknown stopReason, a settled-but-empty message, a 200k answer, a stream that is not JSON, a final event without a trailing newline, a hung process, transcript data leaking onto stderr, and a lockfile-based overlap detector that fails if the session mutex is removed.

Scenarios are chosen with FAKE_MODE; see the header comment for the list and the env switches.

Rules learned the hard way when editing it:

  • Never process.exit() after writing. stdout to a pipe is async and exiting truncates it. Set process.exitCode. This bug once cut a 200k answer short and made a real test lie.
  • process.exitCode does not stop execution. A branch that sets it must also return, or it falls through into the event stream — that is how the --list-models table once got polluted with agent events while substring assertions hid it.
  • Scenarios that must hang set holding = true. They return as soon as their timers are armed, and the rpc path would otherwise read "the function returned" as "the turn is over" and exit — turning a timeout test into an instant clean exit.
  • sh -c execs a single command, replacing its own image and dropping the tag from the command line that pgrep -f matches. Hence sleep 120; true # tag.

Read the full file on GitHub · 72 lines

Changes

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.

  1. 2mo ago First seen · 72 lines · 62 tokens per session scan A 7a7d3e0fb4b9

Subscribe to this mod's changes

testing is a skill published in the GitHub repository minmax/pi-cli-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 953 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.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens