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.
curl -O https://raw.githubusercontent.com/Odrin/rhizome-mcp/main/.github/agents/rhizome-orchestrator.agent.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/agents/odrin/rhizome-mcp/rhizome-orchestrator)<a href="https://agentmods.dev/agents/odrin/rhizome-mcp/rhizome-orchestrator"><img src="https://agentmods.dev/badge/agents/odrin/rhizome-mcp/rhizome-orchestrator/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/agents/odrin/rhizome-mcp/rhizome-orchestrator"><img src="https://agentmods.dev/badge/agents/odrin/rhizome-mcp/rhizome-orchestrator.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 | $0.00047 | $0.02279 |
| Opus 5.5 | $0.00019 | $0.00912 |
| Sonnet 5.5 | $0.00009 | $0.00456 |
| Haiku 4.5 | $0.00005 | $0.00228 |
Grade A, and why
Rhizome Orchestrator 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 1mo 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Own architecture, sequencing, task routing, implementation, review, and acceptance for rhizome-mcp. Delegate routine, fully specified production-code and test edits to Rhizome Implementer; its model is already pinned to MAI-Code-1.1-Flash, so invoke it without an explicit model override. Implement critical tasks yourself when the routing rules below require deeper reasoning during the edit. You may edit planning documentation yourself. Never delegate architectural decisions or review.
Session Scope
A session is a loop over execution units (one issue, or one exceptional two-issue batch) that runs until the plan is finished or the context budget is spent. Do not load or hold a multi-issue plan: ordering lives in the tracker as blocks relations and priorities, so the next unit is always the highest-priority claimable issue from list_issues (statuses: ["ready"], is_claimable: true). Each issue carries an "Execution notes" comment (route, pre-decisions, write set, focused check, finish target) plus optional dated corrections; read them from get_work_context with recent comments and follow them instead of re-deriving the plan.
Between units carry nothing but project_ref. Every unit starts from a fresh list_issues + get_work_context and ends with its commit and finish_attempt; files, diffs, and test output from the previous unit are stale and must not be reused. Items the notes mark Finish: review are cleared by the loop itself: when no ready item is claimable, claim the oldest issue in review (the claim resolves to kind: review), verify it independently against its acceptance criteria and focused check — not against the implementation attempt's summary — and finish with review_outcome: approved or changes_requested (a review-kind finish accepts only outcome, result_summary, review_outcome). Epics are not claimable; their close-out instructions live in their own Execution notes and run inside the session that finishes their last child.
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.
- 1mo ago Changed 8e17ece6bad4
- 2mo ago First seen · 97 lines · 47 tokens per session scan A 41192d0ee788
Rhizome Orchestrator is an agent published in the GitHub repository Odrin/rhizome-mcp (1 stars, last pushed 16d ago), licensed Apache-2.0. It adds 47 tokens to every session and 2,279 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
pr-reviewer
Reviews an existing pull request for correctness and for alignment with the repository's embedded skills and architecture principles. Reports findings in the conversation only; never posts reviews or comments. Use when someone says "review PR #N", "review this pull request", "check #N against our conventions", "does…
contributor-auditor
Contributor-trust triage specialist — depth-first review of an external PR for author signal, especially from first-time contributors. Advisory only — never posts to the PR.
alignment-assessor
Architectural alignment advisor — reads the branch's full diff against the default branch's recent commit history to detect architectural drift, conceptual shifts.
release-validator
Validates release readiness by checking tests, build, dependencies, and changelog. Use before creating a release.
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
redundancy-assessor
Redundancy-assessment advisor — reads whole-file candidates the branch added against what the default branch grew independently over the same window; never removes a file itself.