Borrowing it
Nothing to install: this file belongs to baruchiro/paperless-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/baruchiro/paperless-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/baruchiro/paperless-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/baruchiro/paperless-mcp/agents-md)<a href="https://agentmods.dev/instructions/baruchiro/paperless-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/baruchiro/paperless-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/baruchiro/paperless-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/baruchiro/paperless-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 | $0.00534 | $0.00534 |
| Opus 5.5 | $0.00214 | $0.00214 |
| Sonnet 5.5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
paperless-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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents working in this repository. Human contributors should read CONTRIBUTING.md.
This project is a Model Context Protocol (MCP) server for the Paperless-NGX API, written in TypeScript for Node.
Before writing code
The change must already be agreed in a GitHub issue. If the person directing you has not linked one, stop and ask them to open one first. Do not open a pull request for a change nobody asked for.
Scope
- One behavior change per pull request. Nothing in the diff that the change does not need.
- Do not add CLI flags, environment variables,
manifest.jsonfields, or HTTP endpoints unless the issue asks for them. - Do not change an existing default. That breaks someone's setup and needs its own discussion.
- Do not add hardening, refactoring, or cleanup alongside a feature. Report what you noticed instead of fixing it here.
- Size the change to the problem. No defensive code for states that cannot occur, no abstraction with a single caller, no configuration nobody requested, no duplicate enforcement of the same rule at two layers.
Comments
Write none by default. A comment must carry what the code cannot: a hidden constraint, a non-obvious why, a reference. Never restate the line below it, and never argue the case for your own change — that belongs in the pull request description.
Keep comments and identifiers in English.
Required
- A changeset for every code change: run
npx changesetand commit the generated.changeset/*.md. Documentation-only changes do not take one — a changeset triggers a release. - No scratch, planning, or summary files (
NOTES.md,PLAN.md,REVIEW_SUMMARY.md, and the like). No build artifacts,node_modules, or.envfiles. - No new top-level documentation or governance files unless you were asked for them.
- In code, comments, and config: no references to another repository, or to the setup of whoever is running you. Deliberate attribution in this project's own documentation is fine.
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 · 39 lines · 534 tokens per session scan A 4f7e2ce5f828
paperless-mcp AGENTS.md is an instructions file published in the GitHub repository baruchiro/paperless-mcp (149 stars, last pushed 3d ago), licensed ISC. It adds 534 tokens to every session, about $0.0021 per session on Opus 5.5. A static security scan graded it A with 0 findings. It comes from a forked repository.
paperless-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| paperless-mcp AGENTS.mdbaruchiro/paperless-mcp | Instructions file | 149 | 3d ago | ISC | A | 534 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |