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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/nizoka/pdfnative-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/nizoka/pdfnative-mcp/agents-md/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/agents-md"><img src="https://agentmods.dev/badge/instructions/nizoka/pdfnative-mcp/agents-md.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 | $0.02828 | $0.02828 |
| Opus 5.5 | $0.01131 | $0.01131 |
| Sonnet 5.5 | $0.00566 | $0.00566 |
| Haiku 4.5 | $0.00283 | $0.00283 |
Grade A, and why
pdfnative-mcp AGENTS.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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Condensed, editor-agnostic guidance for AI coding agents working on pdfnative-mcp (Cursor, Aider, Claude Code, Copilot, Continue, Zed, Cline, Windsurf, Goose, Gemini CLI, …). Canonical detail: .github/copilot-instructions.md + .github/instructions/. Claude Code loads CLAUDE.md, which imports this file. Keep the three consistent. Agents that use the server read docs/AGENT_CONTRACT.md (tool catalogue, decision tree, token economy, error codes) instead.
Mission and constraints
pdfnative-mcp is the official Model Context Protocol server of the pdfnative engine: 28 tools over the document lifecycle (generate, sign/verify/LTV, page tree, forms, metadata, encryption, inspection, validation), 7 prompts and resources, on stdio and Streamable HTTP.
- Three runtime dependencies, no more.
pdfnative,@modelcontextprotocol/server,zod. Proposing another runtime package is a hard block (draft_governance_issueandnpm run verify:issueenforce it). - Faithful thin wrapper. Every PDF feature lives in the engine; the server never reimplements one and never over-promises (engine limits are stated in the tool description and in ROADMAP.md).
- Validate at the boundary. Every
tools/callargument comes from a model: each object schema is Zod.strict(), kept in step by hand with the JSON Schema advertised for it; every failure is anisErrorresult with one documentedToolErrorcode — no uncoded failure. - Additive and byte-identical. Default responses of existing tools do not change across releases; new behaviour is opt-in.
Read
docs/API_STABILITY.mdbefore touching a schema or an error code. - Offline by default. The only egress path is
src/network.ts(operator-configured RFC 3161 / OCSP / CRL endpoints, SSRF guard); no tool argument ever supplies a URL or an absolute path. File output stays underPDFNATIVE_MCP_OUTPUT_DIR(src/output.ts). - No secret in any output. Never log or echo passwords, keys, certificates,
PDFNATIVE_MCP_TSA_AUTHorPDFNATIVE_MCP_HTTP_TOKEN; never cache secret-, time- or network-dependent results. - Operator knobs are read once at boot, declared in
server.json, and an invalid value refuses to start — never a silent fallback. - ESM-first TypeScript strict. Relative imports carry
.js; noany; no unused locals; on stdio, stdout carries JSON-RPC frames only (logs go to stderr). - Reproducible output. Dates are written in UTC; a per-call
creationDate,PDFNATIVE_MCP_CREATION_DATEorSOURCE_DATE_EPOCHpins them; the sample set is byte-stable underTZ=UTCand held totests/_fixtures/samples.sha256.json. - Human-in-the-loop. Agents draft and verify; the maintainer pushes, opens PRs/issues, tags and publishes (see Governance).
- English everywhere. Code, comments, tests, examples, docs and release notes are English; demonstrated content in another language
is marked
demo-language: <tag> (reason)on or above the line (verify:docsruleprose-language).
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 · -174 lines · -7,309 tokens per session a96dc01d31cf
- 1mo ago First seen · 295 lines · 10,137 tokens per session scan A 10526d076671
pdfnative-mcp AGENTS.md is an instructions file published in the GitHub repository Nizoka/pdfnative-mcp (2 stars, last pushed 7d ago), licensed MIT. It adds 2,828 tokens to every session, about $0.0113 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.