Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/projectbluefin/bluefin-mcpnpx agentmods add skills/projectbluefin/bluefin-mcp/skillsWrote 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/skills/projectbluefin/bluefin-mcp/skills)<a href="https://agentmods.dev/skills/projectbluefin/bluefin-mcp/skills"><img src="https://agentmods.dev/badge/skills/projectbluefin/bluefin-mcp/skills/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/skills/projectbluefin/bluefin-mcp/skills"><img src="https://agentmods.dev/badge/skills/projectbluefin/bluefin-mcp/skills.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 | $0.00000 | $0.02782 |
| Opus 5 | $0.00000 | $0.01391 |
| Sonnet 5 | $0.00000 | $0.00556 |
| Haiku 4.5 | $0.00000 | $0.00278 |
Grade C, and why
skills scanned grade C with 1 finding 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 10d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
just clean # rm -rf bin/ How it starts
The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bluefin-mcp — Operational Knowledge
When to Use
Load this skill for any work in projectbluefin/bluefin-mcp — Go backend, tools, tests, testdata, CI.
When NOT to Use
For generic Go patterns → standard Go docs. For Bluefin system facts → check projectbluefin/common, ublue-os/bluefin, docs.projectbluefin.io directly.
Design Law — Read Before Changing Anything
Every tool, field, and default value MUST be grounded in:
projectbluefin/commonsource codeublue-os/bluefinsource codedocs.projectbluefin.io
Never design from generic Linux assumptions:
- Wayland only — X11 is completely unsupported on Bluefin. Never add X11 detection, references, or fallbacks.
- No dnf/rpm/apt — the root filesystem is read-only. Package management = flatpak, brew, ujust only.
- Fully read-only server — bluefin-mcp has no write operations except
store_unit_docs. Never add execute functionality. - Before adding any tool or field: verify it exists in Bluefin source or official docs. If not there, it doesn't belong here.
Architecture
bluefin-mcp follows the Ports & Adapters (hexagonal) pattern.
cmd/bluefin-mcp/main.go Entry point. Wires everything together.
internal/cli/executor.go Port: CommandRunner interface
internal/cli/real.go Adapter: RealExecutor (exec.Command)
internal/cli/mock.go Adapter: MockExecutor (test double)
internal/system/ Domain: one file per subsystem
internal/tools/tools.go Thin MCP glue — no business logic
internal/seed/ Embedded seed data (go:embed)
testdata/ Golden files from real Bluefin output
CommandRunner interface
Defined in internal/cli/executor.go:
type CommandRunner interface {
Run(ctx context.Context, name string, args []string) ([]byte, error)
}
ErrNotInstalledis returned when the binary is absent from PATH.- All
internal/system/packages receive an injectedCommandRunner— they never callexec.Commanddirectly. RealExecutor(internal/cli/real.go) runs actual system commands with process-group management so context cancellation can SIGTERM → SIGKILL the process tree.
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.
- 10d ago First seen · 243 lines · 0 tokens per session scan C adf4a0f07330
skills is a skill published in the GitHub repository projectbluefin/bluefin-mcp (5 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,782 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…