What is bluefin-mcp AGENTS.md?

A project guide for bluefin-mcp, a Go service that provides read-only tools for getting information about the Bluefin Linux project.

Use it when working on bluefin-mcp architecture, skills, test data, MCP tools, or project pull-request operations.

It sets boundaries for server changes and pull-request comments, including rules about what agents must not post.

How projectbluefin/bluefin-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to projectbluefin/bluefin-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.

Copy the file

curl -O https://raw.githubusercontent.com/projectbluefin/bluefin-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/projectbluefin/bluefin-mcp

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/projectbluefin/bluefin-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/projectbluefin/bluefin-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/projectbluefin/bluefin-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/projectbluefin/bluefin-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/projectbluefin/bluefin-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/projectbluefin/bluefin-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 918 This file is loaded in full into every session.

When invoked 918 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00918	$0.00918
Opus 5.5	$0.00367	$0.00367
Sonnet 5.5	$0.00184	$0.00184
Haiku 4.5	$0.00092	$0.00092

Measured 2mo ago against content hash b1c2e6dc827f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bluefin-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 2mo 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.

AGENTS.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⛔ Never open upstream PRs. Full rules: cat ~/src/skills/workflow/SKILL.md

projectbluefin/bluefin-mcp

Semantic AI context layer for Bluefin — 11 read-only MCP tools, Go ports-and-adapters architecture. Live binary: ~/.local/bin/bluefin-mcp | Branch: main

PR Comment Policy

One comment per PR event, max. Combine all findings into a single comment. Never post a follow-up comment for a new observation — edit the existing one instead.

Never duplicate GitHub UI state. Do not post approval counts, merge queue status, or CI pass/fail summaries — GitHub already surfaces these natively in the PR timeline.

Test reports: minimal. Report what ran, pass/fail, and blockers only. No diff summaries. No tables unless comparing ≥3 divergent approaches that require a human decision.

@ mentions in context only. Only ping someone if asking them to do something specific. Always inside the combined comment — never as a standalone comment.

When in doubt, don't post. If the only thing to report is "tests pass", post nothing.

Skills

cat skills/SKILL.md                           # repo operational knowledge (architecture, tools, testdata)
cat ~/src/skills/bluefin-mcp/SKILL.md         # cross-cutting Bluefin MCP patterns

Quick Start

just build          # go build -o bin/bluefin-mcp ./cmd/bluefin-mcp
just install        # install to ~/.local/bin/bluefin-mcp
just test           # go test -race ./...
just lint           # go vet ./... && staticcheck ./...
bash scripts/refresh-testdata.sh   # regenerate golden files from upstream Bluefin repos

Server Boundary: linux-mcp-server vs bluefin-mcp

Before adding any tool, check what linux-mcp-server already covers:

linux-mcp-server tool	Covers
`get_system_information`	hostname, OS, kernel, uptime
`get_cpu_information`	CPU model, cores, frequency, load averages
`get_memory_information`	RAM and swap usage
`get_disk_usage`	filesystem usage for all mount points
`get_hardware_information`	lspci (bare, no `-nnk` flags), lscpu, lsusb, dmidecode
`get_service_status` / `get_service_logs`	systemd unit status and journalctl
`get_journal_logs`	journalctl queries
`get_network_interfaces` / `get_network_connections`	network state
`list_processes` / `get_process_info`	process list
`read_file`	reads files from allowlisted paths (covers `/etc`)

Read the full file on GitHub · 77 lines

Changes

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.

2mo ago First seen · 77 lines · 918 tokens per session scan A b1c2e6dc827f

Subscribe to this mod's changes

bluefin-mcp AGENTS.md is an instructions file published in the GitHub repository projectbluefin/bluefin-mcp (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 918 tokens to every session, about $0.0037 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.

bluefin-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bluefin-mcp AGENTS.mdprojectbluefin/bluefin-mcp	Instructions file	5	2mo ago	Apache-2.0	A	918	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

bluefin-mcp: Instructions file for Codex