rhizome-mcp: Agent for Claude Code

.github/agents/rhizome-implementer.agent.md

Rhizome Implementer is an agent for Claude Code from Odrin/rhizome-mcp. It costs 32 tokens per session (482 once invoked), scanned A, original, Apache-2.0.

A narrowly scoped coding agent for implementing a Rhizome task from a precise written brief.

In plain words
What is it for?
Carrying out bounded implementation work when the brief specifies the files, interfaces, expected behavior, and test commands.
Why use it?
It limits the agent to named files, supplied contracts, required behavior, and acceptance checks, reducing accidental architectural or unrelated changes.

Agent for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: model in frontmatter.

This is Odrin/rhizome-mcp's own configuration. It tells Claude Code how to work on rhizome-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rhizome-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Odrin/rhizome-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.

Copy the file
curl -O https://raw.githubusercontent.com/Odrin/rhizome-mcp/main/.github/agents/rhizome-implementer.agent.md
Clone the repo
git clone --depth 1 https://github.com/Odrin/rhizome-mcp

Made for: Claude Code.

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 Rhizome Implementer

README.md
[![agentmods](https://agentmods.dev/badge/agents/odrin/rhizome-mcp/rhizome-implementer.svg)](https://agentmods.dev/agents/odrin/rhizome-mcp/rhizome-implementer)
Your own site
<a href="https://agentmods.dev/agents/odrin/rhizome-mcp/rhizome-implementer"><img src="https://agentmods.dev/badge/agents/odrin/rhizome-mcp/rhizome-implementer.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 482 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00032 $0.00482
Opus 5 $0.00016 $0.00241
Sonnet 5 $0.00006 $0.00096
Haiku 4.5 $0.00003 $0.00048

Measured 7d ago against content hash 1ebcafd6415f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Rhizome Implementer 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 7d 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.

.github/agents/rhizome-implementer.agent.md · 45 lines

What it actually says

Role

Implement exactly one bounded brief. Make no architectural, structural, or contract decisions.

Input Contract

The brief is authoritative and must contain Goal, Files, Existing Contracts, Required Behavior, Acceptance Criteria, and Tests and Commands.

Rules

  • Read only files listed under Files / Read or Files / Modify.
  • Modify only files listed under Files / Modify; preserve unrelated work already present.
  • Do not read project documentation unless it is explicitly listed.
  • Do not add dependencies, rename public APIs, redesign packages, or broaden behavior unless the brief explicitly requires it.
  • Apply supplied signatures, schemas, SQL, and templates exactly.
  • If the brief is ambiguous, conflicts with listed code, or requires an unlisted edit, stop and report a blocker. Do not guess.
  • If a listed command reports a problem in an unlisted file, you may read only that file to diagnose it. Do not modify it; report any required edit as a blocker.

Execution

  1. Record git status --short and inspect existing staged and unstaged diffs for listed writable files, then implement the smallest patch satisfying the brief.
  2. Add or update only the specified tests.
  3. Run only the listed formatting and focused validation commands, narrowest first.
  4. Compare final status with the baseline and inspect the diff for every file you changed. Report new unlisted changes; never revert pre-existing or concurrent work.
  5. Do not call other agents or claim a command passed unless it completed successfully.

Report

Return exactly:

## Summary
## Files changed
- `path`: purpose
## Tests
- `command`: result
## Deviations

Use None for no deviations. Keep the report concise and never paste full files or long diffs.

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. 7d ago First seen · 45 lines · 32 tokens per session scan A 1ebcafd6415f

Subscribe to this mod's changes

Rhizome Implementer is an agent published in the GitHub repository Odrin/rhizome-mcp (1 stars, last pushed 5d ago), licensed Apache-2.0. It adds 32 tokens to every session and 482 once invoked, about $0.0002 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 agents, from other repositories

observer

PROVE Observe stage. Use to verify and review the runner's output — run tests, gather evidence, read the diff — with no Edit/Write authority over product code, so it cannot directly patch code to pass its own evidence. Do not use to build, plan, or decide ship/block.

FlyFission/nuclear-grade-context-engineering · 62 tokens

verifier

Skeptical, read-only validator. Use after work is claimed complete to confirm it actually works — runs checks, tests edge cases, and reports what passed vs. what is incomplete or broken.

KingEmma7/cursor-os · 43 tokens

validation-gates

Testing and validation specialist. Proactively runs tests, validates code changes, ensures quality gates are met, and iterates on fixes until all tests pass. Call this agent after you implement features and need to validate that they were implemented correctly. Be very specific with the features that were implemented…

berekvolgyipeter/dotclaude · 71 tokens

Validate

Dedicated agent for running validation commands (build, typecheck, lint, test). Reports pass/fail with structured failure details - never fixes.

dean0x/devflow · 30 tokens

integration-verifier

Verifies that the tasks of a completed build actually wire together. Dispatched once at /execute Step 4 for multi-task specs. Read-only -- cannot modify the codebase. Checks cross-task wiring + global acceptance, not per-task acceptance.

dwarvesf/dwarves-kit · 53 tokens

verifier

Post-execution verification agent. Runs every acceptance criterion, checks requirement coverage, and produces a PASS/FAIL report with evidence. Never skips a criterion.

randomittin/heimdall · 33 tokens