bluefin-mcp AGENTS.md

bluefin-mcp AGENTS.md is an instructions file for Codex, OpenCode from projectbluefin/bluefin-mcp. It costs 918 tokens per session, scanned A, original, Apache-2.0.

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

In plain words
What is it for?
Use it when working on bluefin-mcp architecture, skills, test data, MCP tools, or project pull-request operations.
Why use it?
It sets boundaries for server changes and pull-request comments, including rules about what agents must not post.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/projectbluefin/bluefin-mcp/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.

agentmods badge for bluefin-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/projectbluefin/bluefin-mcp/agents-md.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.svg" alt="Measured on agentmods" 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. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00918 $0.00918
Opus 5 $0.00459 $0.00459
Sonnet 5 $0.00184 $0.00184
Haiku 4.5 $0.00092 $0.00092

Measured 5d ago against content hash b1c2e6dc827f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 5d 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.

  1. 5d 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 3d ago), licensed Apache-2.0. It adds 918 tokens to every session, about $0.0046 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.

Related

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).

microsoft/vscode · 6,785 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens