Borrowing it
Nothing to install: this file belongs to sfaustodev/Mycorrhiza-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/sfaustodev/Mycorrhiza-MCP/main/CLAUDE.mdgit clone --depth 1 https://github.com/sfaustodev/Mycorrhiza-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/sfaustodev/mycorrhiza-mcp/claude-md)<a href="https://agentmods.dev/instructions/sfaustodev/mycorrhiza-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sfaustodev/mycorrhiza-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/sfaustodev/mycorrhiza-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sfaustodev/mycorrhiza-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 | $0.00924 | $0.00924 |
| Opus 5 | $0.00462 | $0.00462 |
| Sonnet 5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
Mycorrhiza-MCP CLAUDE.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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
Reference implementation of Layer 1 of the Mycorrhiza proposal: a local MCP server that gives any MCP client (Claude Desktop, Cursor, Continue, …) persistent memory backed by a SHA-256 hash chain stored in SQLite. Three tools exposed: remember, recall, chain_status. See README.md for the conceptual framing and v0.2/v1.0 roadmap (cristalização, herança ativa).
Commands
Local dev setup:
python3 -m venv .venv && source .venv/bin/activate
pip install -e .
Run the server (stdio, what an MCP client invokes):
python -m mycorrhiza.server
# or, after install:
mycorrhiza-mcp
Inspect tools interactively (FastMCP dev inspector, ships with mcp[cli]):
mcp dev mycorrhiza/server.py
Use an isolated chain for experiments — point MYCORRHIZA_DB at a throwaway path so you don't pollute the user's real chain at ~/.mycorrhiza/chain.db:
MYCORRHIZA_DB=/tmp/test-chain.db python -m mycorrhiza.server
No test suite, linter, or CI is configured. Don't fabricate commands; if you add tooling, wire it through pyproject.toml.
Architecture
Single module: mycorrhiza/server.py. Roughly four layers, top to bottom:
- Storage path resolution —
DB_PATHfromMYCORRHIZA_DBenv or~/.mycorrhiza/chain.db; parent dir auto-created. State is local-only, no network, no auth. - Hash function —
_compute_hash(seq, ts, prev_hash, content, tags)serializes a JSON object withsort_keys=True, ensure_ascii=Falseand SHA-256s it. Field order/serialization is the integrity contract: any change breakschain_statusretroactively. - Schema bootstrap —
_init_db()creates the singlechaintable (seqPK,ts,prev_hash,content,tagsas JSON-encoded array,hashUNIQUE) and an index onts DESC. Idempotent, called at import time. - MCP tools (
@mcp.tool()on aFastMCP("mycorrhiza")instance):remember— reads tail link, computes next link's hash chained on prev's hash, inserts. Genesis sentinel for the first link is the literal string"genesis".recall—SELECT … WHERE content LIKE ? AND tags LIKE ?with case-insensitive substring match; tag filter is a textual%"tag"%over the JSON array (good enough for Layer 1, swap if scale demands).chain_status— walks the chain fromseq=1, recomputes each hash, and verifies bothprev_hashlinkage and stored-hash integrity. Reports first break.
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.
- 8d ago First seen · 63 lines · 924 tokens per session scan A 50b3d9993aff
Mycorrhiza-MCP CLAUDE.md is an instructions file published in the GitHub repository sfaustodev/Mycorrhiza-MCP (2 stars, last pushed 1mo ago), licensed MIT. It adds 924 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.
Other instructions, from other repositories
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
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.
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.
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).
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).
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.