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/instructions/testing.instructions.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/instructions/nizoka/pdfnative-mcp/testing)<a href="https://agentmods.dev/instructions/nizoka/pdfnative-mcp/testing"><img src="https://agentmods.dev/badge/instructions/nizoka/pdfnative-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.
<a href="https://agentmods.dev/instructions/nizoka/pdfnative-mcp/testing"><img src="https://agentmods.dev/badge/instructions/nizoka/pdfnative-mcp/testing.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 | $0.01219 | $0.01219 |
| Opus 5.5 | $0.00488 | $0.00488 |
| Sonnet 5.5 | $0.00244 | $0.00244 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
pdfnative-mcp testing.instructions.md 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Standards
The gate
npm run gate(CI profile) is the single definition of green;npm run gate:fastwhile iterating;npx tsx scripts/gate.ts --publish --require-allbefore a release (needs veraPDF). One line per step, logs undertest-output/.gate/. Summarise its output — do not paste logs.- PowerShell swallows a bare
--afternpm run: callnpx tsx scripts/<name>.ts <flags>directly. - Build before the suites that need
dist/:tests/cli-stdio.test.ts,tests/reproducible-build.test.ts(they skip locally, fail under CI /GATE_REQUIRE_ARTIFACTS=1)..npmrcdisables install-time scripts.
Framework
- vitest 4,
TZ=UTC,pool: 'forks', no shuffle,dotreporter. Tests are flat undertests/; shared fixtures are_-prefixed; repository-tooling tests live intests/tools/. - Commands:
npm test,npm run test:coverage,npm run typecheck:all(src + tests + scripts),npm run lint(eslint src --max-warnings 0— warnings fail),npm run examples:check. - Coverage thresholds live once, in
vitest.config.ts. Never lower them; raise them when a release lifts coverage.
Catalogue parity
tests/catalogue-parity.test.tscompares the livetools/liststructure withtests/_fixtures/tool-shape.json.- After a deliberate schema change:
npm run build && npx tsx scripts/tool-shape.ts --write, then review the fixture diff under docs/API_STABILITY.md §5. Never refresh it to silence an accidental change. tests/catalogue-superset.test.tscompares the live catalogue with the frozentests/_fixtures/tool-shape.v1.5.0.json: no tool / property / enum value removed, no newrequired, no tighter bound; every accepted delta is enumerated in the test and must still occur. Never regenerate the 1.5.0 fixture.tests/error-codes.test.tsinventories everyToolErrorcode insrc/and assertsdocs/AGENT_CONTRACT.md§6 documents it and a test names it.
Samples and the byte baseline
npm run build && npm run test:generatedrives the BUILT server and writestest-output/samples/;npm run verify:samplescompares it withtests/_fixtures/samples.sha256.json. The baseline is a chain: an unchanged entry keeps itssince.- An intended output change is rebaselined with
npx tsx scripts/verify-samples.ts --update, explained in the manifest'sprovenancenote and declared in the release notes. Never--updateto silence a surprise. - A sample that cannot repeat its bytes (CSPRNG, per-run key, TSA clock) is listed explicitly in
ENCRYPTED_SAMPLES/SIGNED_SAMPLES/TIMESTAMPED_SAMPLES/HOST_DEPENDENT_SAMPLES(a result that reports the host, such asdraft_governance_issue;scripts/lib/sample-fingerprint.ts) — prove it with a double run first.
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 · +3 lines · +720 tokens per session 8128eaacc729
- 1mo ago First seen · 43 lines · 499 tokens per session scan A d1cb27d3eb9e
pdfnative-mcp testing.instructions.md is an instructions file published in the GitHub repository Nizoka/pdfnative-mcp (2 stars, last pushed 7d ago), licensed MIT. It adds 1,219 tokens to every session, about $0.0049 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.