Borrowing it
Nothing to install: this file belongs to vexxvakan/mcp-docsrs. 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/vexxvakan/mcp-docsrs/main/AGENTS.mdgit clone --depth 1 https://github.com/vexxvakan/mcp-docsrsWrote 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/vexxvakan/mcp-docsrs/agents-md)<a href="https://agentmods.dev/instructions/vexxvakan/mcp-docsrs/agents-md"><img src="https://agentmods.dev/badge/instructions/vexxvakan/mcp-docsrs/agents-md.svg" alt="Measured on agentmods" 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 | $0.00430 | $0.00430 |
| Opus 5 | $0.00215 | $0.00215 |
| Sonnet 5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
mcp-docsrs 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 8d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents Guidelines
We are running multiple agents on the same code base so you can expect changes in the active commit not authored by you. Do not reset or otherwise touch them and stay only at your edited files scope for your session.
Workflow
- Research code base, documentation and node_modules for information on the given task
- Convert the given task into an actionable plan using
update_planaggressively. - Read the plan back often and mark done steps immediatly after completion.
Documentation
- Use the available Bun documentation inside node_modules/bun-types/docs/ when you are working with Bun to get CONCRETE information. Research the available direct types thoroughly as well.
Code Style
- Do not care for backwards compatibility at all.
- APIs can and should break, we are in active development.
- Do not create too many files in one directory. If the directory is larger than 5 .ts files you need to create a new further split sub directory
- Prefer functional design patterns, convert existing class-based structure into functional style as well and keep public method and variable names concise (maximum two words, exceptions exist).
- Keep concerns seperated in well-structured directories and files. Massive monolith files are terrible design. No file can be longer than 300 lines.
- Remove functions entirely when they are clean to remove.
- Do not keep artifacts for API confirmness or useless type aliases.
- Clean up types after function removal as well.
- Do not clutter or break project structure:
- Types belong in each directory's local
types.tsfile. - Types should be implemented as Type not Interface.
- Types belong in each directory's local
- Always keep test files in sync with code changes. When updating code always check if the respective test needs updating too.
Task Completion
bun checkandbun lint:fixhave to be entirely green for the touched files in this session.- Test your updated or changed functionality by running direct tests of the touched files: Change in
src/docs->bun test src/docs - Coverage for your changes must be at 90% or higher.
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.
- 8d ago First seen · 35 lines · 430 tokens per session scan A a066ef6a959c
mcp-docsrs AGENTS.md is an instructions file published in the GitHub repository vexxvakan/mcp-docsrs (13 stars, last pushed today), licensed Apache-2.0. It adds 430 tokens to every session, about $0.0022 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.