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.
npx agentmods add instructions/odrin/rhizome-mcp/agents-mdgit clone --depth 1 https://github.com/Odrin/rhizome-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/odrin/rhizome-mcp/agents-md)<a href="https://agentmods.dev/instructions/odrin/rhizome-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/odrin/rhizome-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.00236 | $0.00236 |
| Opus 5 | $0.00118 | $0.00118 |
| Sonnet 5 | $0.00047 | $0.00047 |
| Haiku 4.5 | $0.00024 | $0.00024 |
Grade A, and why
rhizome-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.
What it actually says
Agent Guidelines
Use the configured rhizome-mcp server as the source of truth for active work and durable decisions.
Workflow
Claim tracked work through the rhizome-mcp server before editing. Keep the returned lease token private and available until the attempt completes, renewing before expiry and saving restartable checkpoints. Finish every attempt with its truthful outcome, verification actually performed, and next steps.
See the agent workflow guide for the complete select/claim/execute/finish workflow.
Never write in_progress; it is derived from an active lease. Never maintain the backlog or implementation status in Markdown.
Read rhizome://guides/agent-workflow for the full workflow, rhizome://guides/issue-lifecycle for state rules, and rhizome://guides/multi-agent-handoff for recovery. Use the rhizome-task-workflow skill when executing tracked work.
Build and test commands are in README.md; implementation contracts are indexed by SPEC.md.
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.
- 5d ago First seen · 16 lines · 236 tokens per session scan A 909d4b0175be
rhizome-mcp AGENTS.md is an instructions file published in the GitHub repository Odrin/rhizome-mcp (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 236 tokens to every session, about $0.0012 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
hop AGENTS.md
Instructions for amittamari/hop, covering agent map, start here, what this repo builds, working rules and common commands.
superpowers-evals AGENTS.md
AGENTS.md instructions for prime-radiant-inc/superpowers-evals, a project described as: Behavioral eval lab (Quorum) for the superpowers project that drives real coding-agent CLIs (Claude, Codex, Gemini, Kimi, and more) through a QA agent and grades them on workflow compliance against scenario criteria and…
forge AGENTS.md
AGENTS.md instructions for ForgeAILab/forge, a project described as: AI coding agent workflow engine for structured task lifecycles.
universal-remote-control CLAUDE.md
Claude Code instructions for sidkandan/universal-remote-control, covering urc — rc bridge + cli-to-cli communication, quick start, development rules, architecture (v3) and communication strategy.
simple-man CLAUDE.md
Claude Code instructions for Maksim-Burtsev/simple-man, a project described as: Cut the chatter. Keep the work. A measured communication policy for coding agents: −32% output tokens, zero lost facts.
spellbook AGENTS.md
AGENTS.md instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.