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/skills/rhizome-task-workflow/SKILL.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/skills/odrin/rhizome-mcp/rhizome-task-workflow)<a href="https://agentmods.dev/skills/odrin/rhizome-mcp/rhizome-task-workflow"><img src="https://agentmods.dev/badge/skills/odrin/rhizome-mcp/rhizome-task-workflow/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/skills/odrin/rhizome-mcp/rhizome-task-workflow"><img src="https://agentmods.dev/badge/skills/odrin/rhizome-mcp/rhizome-task-workflow.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 | $0.00037 | $0.00293 |
| Opus 5.5 | $0.00015 | $0.00117 |
| Sonnet 5.5 | $0.00007 | $0.00059 |
| Haiku 4.5 | $0.00004 | $0.00029 |
Grade A, and why
rhizome-task-workflow 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 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.
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
Rhizome Task Workflow
- Call
open_projectwith the absolute repository root. Retain itsproject_refand pass it to every later project-scoped tool call. - Find claimable work with
get_planning_graphorlist_issuesusing thatproject_ref. - Read
get_work_context, then claim exactly one issue before editing. - Renew long leases and save restartable checkpoints with artifacts.
- Finish every attempt with its truthful outcome, verification, and next steps.
Use:
- Agent workflow for the complete select/claim/execute/finish workflow.
- Issue lifecycle for statuses, blockers, relations, and concurrency.
- Multi-agent handoff for interruption, recovery, and review.
These three files are generated from the MCP server guides by go generate ./internal/adapters/mcp/... and must not be edited by hand.
The equivalent server guides are linked in the metadata returned by open_project and get_project.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 24 lines · 37 tokens per session scan A 2a38a6a40d9a
rhizome-task-workflow is a skill published in the GitHub repository Odrin/rhizome-mcp (1 stars, last pushed 16d ago), licensed Apache-2.0. It adds 37 tokens to every session and 293 once invoked, about $0.0001 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 skills, from other repositories
work-schedules-and-bots
Manage Crew's message-only project schedules, authenticated webhook triggers, Slack or WhatsApp project-chat bots, and connected Gmail accounts. Use when the user asks for recurring work, event-driven work, a scheduled message, an API trigger, bot routing, email notifications, or reading Gmail in a Crew project.
work-workflow-files
Read and interpret attached folders or read-only AgentWorks workflow references in Crew, invoke an attached workflow through its Crew-scoped internal trigger, and securely link files from the active Crew project. Use when the user asks what an attached workflow contains, wants it run, requests data or Dashboards from…
work-skills
Discover, install, import, create, select, and remove reusable skills in Crew. Use when the user asks to add a capability or manage the skills available to a project or account.
work-ui-control
Present the correct Crew project panel with acknowledged UI control. Use when opening, refreshing, or checking a Crew workspace view; do not use Workflow view IDs or semantics.
background-work
Run a bounded research, analysis, writing, coding, or file task asynchronously and rely on Crew's automatic completion notification instead of polling.
conventional-commit
Rules for writing Conventional Commits messages in this project. MUST be invoked every time a commit is created.