Borrowing it
Nothing to install: this file belongs to cfpperche/picode. 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/cfpperche/picode/main/.pi/skills/quality-gate/SKILL.mdgit clone --depth 1 https://github.com/cfpperche/picodeWrote 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/cfpperche/picode/quality-gate)<a href="https://agentmods.dev/skills/cfpperche/picode/quality-gate"><img src="https://agentmods.dev/badge/skills/cfpperche/picode/quality-gate/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/cfpperche/picode/quality-gate"><img src="https://agentmods.dev/badge/skills/cfpperche/picode/quality-gate.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 | $0.00776 |
| Opus 5.5 | $0.00022 | $0.00310 |
| Sonnet 5.5 | $0.00011 | $0.00155 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
quality-gate 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 1mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality gate
Run this before declaring any code work done in PiCode. The rules come
from docs/benchmarks.md (engineering section) and AGENTS.md. Be honest —
a failed gate reported honestly beats a passed gate reported falsely.
The mechanical part is one command (ADR-0086)
make ci-scoped # while iterating: only the gates this diff can break
make close # at the end: gates + regenerated artifacts + ff check + summary
make close refuses a dirty tree, reuses a green ci-scoped when the tree
did not change, regenerates OpenAPI/llms.txt when the diff invalidated them
(and commits them), and tells you whether main can fast-forward. Public
captures refresh at make deploy, not here. Do not hand-run
gofmt/vet/tests/build one by one in twenty turns; if close fails, fix the
cause and rerun it. Run this gate and the closing docs in a subagent or a
fresh session (ADR-0105): the working session ends at the merge.
The judgement part (read the diff: git diff --stat main...HEAD)
- One logical change? If not, split the commit.
- New code without tests? Table-driven tests before finishing.
- Interacting conditions (delete/restore/auth/cascade/mode)? A decision table exists and every row is tested or named as debt. Two clicks ≠ matrix.
- Timed UI (jobs, overlays, lists)? Motion on enter/step/exit; the optimistic next state, not a static wait then a jump.
- New non-stdlib dependency? Justified in the commit/PR description (AGENTS.md rule #3). No justification = remove it.
- Store mutation without an event, or a new poll against
/api/*without a stated reason the feed cannot cover (ADR-0048) → FAIL. - Changelog: user-visible → a fragment
docs/changelog.d/<branch>.md(neverCHANGELOG.md; the hook refuses it). - Docs: behavior/architecture changed → the
docs/architecture/file for that subsystem; a boundary (protocol, persistence, security, process) →make adr NAME=x. - Visual gate (any user-facing surface changed):
/skill:visual-reviewand/skill:uiux-reviewon a scratch instance (scripts/qa-scratch.sh), never on production. Screenshots read, overlayAudit ok, visual-card in the reply. Skipped or FAIL → this gate is FAIL.evalJSON is not a visual pass. - Handoff:
/skill:handoff-update(one note indocs/handoff/).
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.
- 1mo ago First seen · 61 lines · 56 tokens per session scan A 75cceea93fe9
quality-gate is a skill published in the GitHub repository cfpperche/picode (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 776 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 2026-09-12.
Other skills, from other repositories
code-guidelines-go
Go 1.24–1.27 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or refactoring ANY Go code in pi-go. This covers idiomatic style, error handling, concurrency, project layout, testing (table-driven, fuzz, benchmarks, synctest), new stdlib usage, golangci-lint v2…
vhs-e2e-gif
Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…
code-review-pi
Review code for quality, run linters, check test coverage, fix issues, and enforce gates. Save the final report to ./specs/issues/003-code-review-pi/PROMPT.md. Use before committing changes.
adversarial-implementation-review-coach
Adversarial implementation review based on Block's g3 dialectical autocoding research. Use when validating implementation completeness against requirements with fresh objectivity.
pstack-correct
Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /skill:pstack-correct.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.