Borrowing it
Nothing to install: this file belongs to Nizoka/pdfnative-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/Nizoka/pdfnative-mcp/main/.github/prompts/quality-gate.prompt.mdgit clone --depth 1 https://github.com/Nizoka/pdfnative-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/commands/nizoka/pdfnative-mcp/quality-gate)<a href="https://agentmods.dev/commands/nizoka/pdfnative-mcp/quality-gate"><img src="https://agentmods.dev/badge/commands/nizoka/pdfnative-mcp/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/commands/nizoka/pdfnative-mcp/quality-gate"><img src="https://agentmods.dev/badge/commands/nizoka/pdfnative-mcp/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 | $0.00019 | $0.00491 |
| Opus 5.5 | $0.00008 | $0.00196 |
| Sonnet 5.5 | $0.00004 | $0.00098 |
| Haiku 4.5 | $0.00002 | $0.00049 |
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.
What it actually says
Quality Gate
Run THE gate and report its result. Do not run the individual steps by hand.
Steps
npm run gate(CI profile, the default). When the user asks for a quick check, runnpm run gate:fastinstead; on a release branch,npx tsx scripts/gate.ts --publish --require-all. (PowerShell swallows a bare--, so pass gate flags by calling the script directly.)- Report the gate's own summary verbatim — it is at most 20 lines. Do not paste step logs into the conversation.
- For a failing step only, open
test-output/.gate/<step>.logthrough the shell (Claude Code is deniedRead(test-output/**)) and quote the smallest excerpt that explains the failure. - Re-run a single step after a fix with
npx tsx scripts/gate.ts --only <step>;--jsongives machine-readable output.
What each profile contains
The step list is the STEPS table in scripts/gate.ts — read it there rather than from this prompt, so the two never drift. The smoke step drives the BUILT server (dist/cli.js) over stdio and fails on any stdout line that is not a JSON-RPC frame, so build precedes it; validate:pdfa is skipped without veraPDF unless --require-all turns the skip into a failure.
Quality thresholds
- Zero TypeScript errors (two configs:
src+tests, andscripts), zero ESLint errors and warnings. - All tests passing; coverage thresholds are declared once in
vitest.config.tsand enforced by the gate. - The built
tools/listmatchestests/_fixtures/tool-shape.json(verify:tool-shape);server.jsonvalidates against the vendored registry schema (server-json). - Counts and versions quoted in docs must match
docs/assets/ecosystem.json(verify:docsstep). - Every generated sample matches
tests/_fixtures/samples.sha256.json(verify:samplesstep); a rebaseline is declared in the release note.
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 Changed · -1 lines · +1 tokens per session c0f8dedb0096
- 1mo ago First seen · 28 lines · 18 tokens per session scan A 2d51babea492
quality-gate is a command published in the GitHub repository Nizoka/pdfnative-mcp (2 stars, last pushed 7d ago), licensed MIT. It adds 19 tokens to every session and 491 once invoked, about $0.0001 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 2026-09-24.
Other commands, from other repositories
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
verify
Run repository verification using the verification-loop skill.
modernize-transform
Transform one legacy module to the target stack — idiomatic rewrite with behavior-equivalence tests.
constraints
A command for defining a project's quality standards through a short interview and a written CONSTRAINTS.md file. It records checks, thresholds, exceptions, and commands for enforcing them.
check-dev
Type-check a Z specification with fuzz.