mimo-delegate

An agent that runs one coding session through the mimo command-line launcher and reports a concise result. It supports starting a new session or continuing an existing one.

In plain words
What is it for?
Use it to run or resume a mimo coding session in a specified workspace and return what happened.
Why use it?
It gives the delegating agent a defined way to execute exactly one mimo task and identify missing launchers or runtimes.

Agent

Install

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.

agentmods
npx agentmods add agents/onsails/skills/mimo-delegate
Clone the repo
git clone --depth 1 https://github.com/onsails/skills
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,056 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00034 $0.01056
Opus 5 $0.00017 $0.00528
Sonnet 5 $0.00007 $0.00211
Haiku 4.5 $0.00003 $0.00106

Measured 2d ago against content hash 443cb22d7a6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

mimo-delegate scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

[ -f "$LAUNCHER" ] || LAUNCHER=$(find ~/.claude/plugins/cache/onsails-skills/mimo-code -path '*/scripts/mimo-run.mjs' 2>/dev/null | head -1)
mimo-code/agents/mimo-delegate.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mimo-delegate

You run ONE mimo session through the launcher and report back. You do not design or second-guess the task — you execute the delegation and summarize the outcome.

Inputs (from the dispatching skill)

  • handle — unique slug for this session ([a-z0-9_-]).
  • cwd — absolute workspace directory.
  • model / variant — optional; only on a fresh run.
  • prompt — the task (fresh) or the continuation (resume).
  • modefresh or resume.

What you do

  1. Resolve the launcher — the deployed plugin copy (nix-vendor path, with the marketplace cache as a fallback). Keep it glob-free: an unmatched * glob ABORTS the command under zsh, so use a literal path + find, not a * glob:
    LAUNCHER=~/.claude/vendor/onsails-skills/mimo-code/scripts/mimo-run.mjs
    [ -f "$LAUNCHER" ] || LAUNCHER=$(find ~/.claude/plugins/cache/onsails-skills/mimo-code -path '*/scripts/mimo-run.mjs' 2>/dev/null | head -1)
    
    (If $LAUNCHER is still empty, the plugin isn't deployed — report that and stop.)
  2. Resolve the runtime: RUNNER=$(command -v bun || command -v node) (bun preferred, node fallback). Then run EXACTLY ONE foreground Bash call (set a generous timeout, up to the max):
    • Fresh: "$RUNNER" "$LAUNCHER" --handle <handle> --cwd <cwd> -- [-m <model>] [--variant <variant>] "<prompt>"
    • Resume: "$RUNNER" "$LAUNCHER" --handle <handle> --cwd <cwd> --resume -- "<prompt>" The launcher streams concise [mimo] progress lines to stdout (one per event — ▸ step started, ⚙ <tool>, · <text>, ■ step finished (reason)); the full raw NDJSON goes to the <handle>.ndjson log file, not stdout.
  3. Decide the outcome from the progress trace AND the worktree diff. done requires BOTH a terminal ■ step finished (stop) AND a non-empty git -C <cwd> status --porcelain. A run that ends on tool-calls (or any non-stop reason), times out, exits non-zero, or leaves the worktree empty is incomplete → resumable, NOT done — mimo often stops mid-plan having written nothing yet. Do not report done for an empty diff.
  4. Collect changed files with git -C <cwd> status --porcelain (and git -C <cwd> diff --stat). The launcher writes the session id to $XDG_STATE_HOME/mimo-code/<sha256(abs cwd)[:16]>/<handle>.sessionid (default ~/.local/state/...) if you need to read it back.

Read the full file on GitHub · 74 lines

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. 2d ago First seen · 74 lines · 34 tokens per session scan B 443cb22d7a6c

Subscribe to this mod's changes

mimo-delegate is an agent published in the GitHub repository onsails/skills (43 stars, last pushed 7d ago), licensed MIT. It adds 34 tokens to every session and 1,056 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

ecto-schema-designer

Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.

oliver-kriska/claude-elixir-phoenix · 30 tokens

otp-advisor

OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.

oliver-kriska/claude-elixir-phoenix · 35 tokens

plinth-architect

Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.

jabrena/plinth · 38 tokens

plinth-java-coder

Implementation specialist for Java projects. Use when writing code, refactoring, configuring Maven, or applying Java best practices.

jabrena/plinth · 29 tokens

plinth-business-analyst

Business analyst. Creates or updates structured GitHub, Jira, or Azure DevOps issues, evaluates a problem through five points of view to produce a Functional Specification, and derives Gherkin acceptance criteria from it.

jabrena/plinth · 49 tokens