Borrowing it
Nothing to install: this file belongs to rogermt/mcp-repo-onboarding. 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/rogermt/mcp-repo-onboarding/master/AGENTS.mdgit clone --depth 1 https://github.com/rogermt/mcp-repo-onboardingWrote 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/rogermt/mcp-repo-onboarding/agents-md)<a href="https://agentmods.dev/instructions/rogermt/mcp-repo-onboarding/agents-md"><img src="https://agentmods.dev/badge/instructions/rogermt/mcp-repo-onboarding/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/rogermt/mcp-repo-onboarding/agents-md"><img src="https://agentmods.dev/badge/instructions/rogermt/mcp-repo-onboarding/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 | $0.02056 | $0.02056 |
| Opus 5 | $0.01028 | $0.01028 |
| Sonnet 5 | $0.00411 | $0.00411 |
| Haiku 4.5 | $0.00206 | $0.00206 |
Grade A, and why
mcp-repo-onboarding 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 9d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Agent & Copilot Instructions
Current Status
- Phase 7 (Domain Specialization): COMPLETE (Notebook detection, Prompt/Tool UX).
- Phase 8 (Refinement): ACTIVE (Determinism, Maintainability, Scaffold).
- Validation Authority:
scripts/validate_onboarding.pyis the source of truth for all code generation.
Output Verification
When verifying output, ensure no files from tests/fixtures/ appear in the lists. Refer to EXTRACT_OUTPUT_RULES.md for the priority order.
Project Identity
- Name:
mcp-repo-onboarding - Language: Python 3.11+ (100% Python scope)
- Manager:
uv - Architecture: FastMCP (Server), Pydantic (Schema), Pytest (Testing).
- Stable API (Tools):
ping,analyze_repo,get_run_and_test_commands,read_onboarding,write_onboarding,get_onboarding_template. - Stable API (Prompts):
generate_onboarding(Slash command:/generate_onboarding).
⚠️ CRITICAL: TDD Required
ALL code changes MUST follow Test-Driven Development:
- NEVER commit directly to the
masterbranch. All changes must be verified in a feature branch first. - Write failing test FIRST in
tests/. - Run test to confirm failure (
uv run pytest). - Implement the fix in
src/. - Run test to confirm pass (
uv run pytest).
NO EXCEPTIONS. Do not write logic without a red test first.
⚠️ CRITICAL: Agent Must Never Write to evaluation_results.log
The agent MUST NOT modify, write to, or update evaluation_results.log under ANY circumstances.
This file is managed by the user only:
- Agent runs
uv run python scripts/validate_onboarding.pyto verify output - Agent displays the output to the user
- Agent NEVER writes to
evaluation_results.log - User is solely responsible for updating this file
⚠️ CRITICAL: Trust the Plan and Documentation
FOLLOW THE PLAN. Do NOT deviate or second-guess:
- If AGENTS.md or approved plan says master is clean → trust it. Do not "check" old commits.
- If a plan specifies test structure → follow it exactly. Do not restore old commits thinking things are broken.
- Always read the current documentation first. Do not assume state based on suspicion.
- If status is documented (e.g., "Phase 7 COMPLETE"), do not undo or redo it.
- Fetch from origin before making assumptions about branch state.
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.
- 9d ago First seen · 169 lines · 2,056 tokens per session scan A 132f3f0b310f
mcp-repo-onboarding AGENTS.md is an instructions file published in the GitHub repository rogermt/mcp-repo-onboarding (2 stars, last pushed 2mo ago), licensed MIT. It adds 2,056 tokens to every session, about $0.0103 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 2026-08-31.
Other instructions, from other repositories
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.