Borrowing it
Nothing to install: this file belongs to abel30567/fermi-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/abel30567/fermi-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/abel30567/fermi-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/abel30567/fermi-mcp/agents-md)<a href="https://agentmods.dev/instructions/abel30567/fermi-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/abel30567/fermi-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/abel30567/fermi-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/abel30567/fermi-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 | $0.00943 | $0.00943 |
| Opus 5.5 | $0.00377 | $0.00377 |
| Sonnet 5.5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
fermi-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 yesterday.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent rules
Development pattern: orchestrator + independent workers
Work is done by headless agent workers, one task each, in isolated git worktrees, coordinated
through pull request comments. Nothing merges until an independent verifier has signed off on the
exact head commit. Tooling: .agents/orchestrator/ (orch help).
Roles
| Role | Runs as | Does |
|---|---|---|
| Orchestrator | you + your interactive agent session | Triages tasks, gathers inputs workers cannot reach, launches workers, runs the merge gate, releases. The only role that merges. |
| Builder | orch launch builder KEY slug "TASK" |
Own worktree and branch. Builds, runs every gate, opens the PR, posts [BUILDER] READY, exits. |
| Verifier | orch launch verifier PR "criteria" |
Fresh detached worktree. Adversarial: re-runs the gates itself and tries to break every criterion. Never pushes. |
| Fixer | orch launch fixer PR "focus" |
Addresses every finding, merges the base, posts [BUILDER] ADDRESSED. |
| Blast radius | orch launch br PR "focus" |
Only for risky PRs (orch risk PR). Proves by running code what the change cannot break outside its diff. |
PR comment markers (only a comment's FIRST line counts)
| Marker | By | Content |
|---|---|---|
[BUILDER] READY |
builder | head SHA, gate table, evidence (command → result) per acceptance criterion |
[VERIFIER] CHANGES REQUESTED |
verifier | Reviewed head <sha>, findings F1..Fn: criterion, evidence, repro command |
[BUILDER] ADDRESSED |
fixer | per finding: fix + commit SHA, or a reasoned rebuttal |
[VERIFIER] VERIFIED |
verifier | Reviewed head <sha>, evidence table for every criterion |
[BLAST-RADIUS] SAFE / UNSAFE |
blast radius | Reviewed head <sha>, the one fact that makes it safe and the command that proved it |
[BUILDER] BLOCKED |
builder/fixer | Missing / What was tried / Resume from (branch @ sha) |
[ORCHESTRATOR] … |
orchestrator | binding rulings, merge notes |
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.
- yesterday First seen · 58 lines · 943 tokens per session scan A d8f972c26312
fermi-mcp AGENTS.md is an instructions file published in the GitHub repository abel30567/fermi-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 943 tokens to every session, about $0.0038 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 2026-10-23.
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.
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.
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).