Borrowing it
Nothing to install: this file belongs to SoftBacon-Software/mycelium-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/SoftBacon-Software/mycelium-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/SoftBacon-Software/mycelium-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/softbacon-software/mycelium-mcp/claude-md)<a href="https://agentmods.dev/instructions/softbacon-software/mycelium-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/softbacon-software/mycelium-mcp/claude-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/softbacon-software/mycelium-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/softbacon-software/mycelium-mcp/claude-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 | $0.01393 | $0.01393 |
| Opus 5.5 | $0.00557 | $0.00557 |
| Sonnet 5.5 | $0.00279 | $0.00279 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade A, and why
mycelium-mcp CLAUDE.md scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
MCP (Model Context Protocol) server that wraps the Mycelium platform API as native Claude Code tools. Package name: `mycelium-mcp`. Gives Claude agents tools like `mycelium_boot`, `mycelium_claim_task`, `mycelium_heartbe How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Mycelium MCP Server
What This Is
MCP (Model Context Protocol) server that wraps the Mycelium platform API as native Claude Code tools. Package name: mycelium-mcp. Gives Claude agents tools like mycelium_boot, mycelium_claim_task, mycelium_heartbeat instead of raw curl commands. (Tools are defined internally under legacy studio_* names and registered as mycelium_* only — the studio_* aliases were dropped to stay under MCP tool limits.)
Critical Rules
- No guessing: If info isn't in context, say "I don't know" or use a tool to fetch it.
- No silent failures: Report failures immediately. Never pretend something worked.
- Evidence-based: Verify files exist before editing. Read before writing.
- Honest failure: Failing is OK. Never force "success" by modifying tests or deleting checks.
Commands
node index.js # Run MCP server (stdio transport)
npm install # Install dependencies
npm test # smoke gate + handler tests (no framework, Node builtins only)
Tests: test/smoke.mjs (syntax/import/export gate over every source file) and
test/handlers.test.mjs (api client + tool handlers against a local mock
substrate, plus an entry-point boot/shutdown gate). Run green before any publish.
Layout
index.js # Entry point — MCP server setup, env validation, shutdown wiring
src/
api.js # HTTP client for Mycelium API (fetch wrapper, timeouts, error context)
state.js # Session state, auto-heartbeat (5min interval)
sse.js # SSE event stream client (reconnect with backoff)
tools.js # All MCP tool definitions and handlers
test/ # npm test — zero-dependency gates (not published to npm)
package.json # mycelium-mcp
Architecture
- Transport: stdio (standard MCP pattern)
- Two modes:
admin(full access, X-Admin-Key) andagent(scoped, X-Agent-Key, auto-heartbeat) - API target: Defaults to
https://mycelium.fyi/api/mycelium. Configurable viaMYCELIUM_API_URL. - Tool naming: All tools registered with
mycelium_*prefix only (legacystudio_*names exist in source but are not registered — dropped to stay under tool limits). - Auto-heartbeat: In agent mode, sends heartbeat every 5 minutes. Clears
working_onon shutdown.
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 · 118 lines · 1,393 tokens per session scan A d7ec8c204cc3
mycelium-mcp CLAUDE.md is an instructions file published in the GitHub repository SoftBacon-Software/mycelium-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,393 tokens to every session, about $0.0056 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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).
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.