midas-harness: Skill for Claude Code

.agents/skills/midas-auto-pilot/SKILL.md

midas-auto-pilot is a skill for Claude Code, Codex from okuzpe/midas-harness. It costs 67 tokens per session (2,923 once invoked), scanned A, original, Apache-2.0.

A Midas workflow for deciding and carrying out autonomous project work. It asks whether the task is ongoing improvement or a sprint, then reports status, delivery mode, warnings, and evidence in a short fixed format.

In plain words
What is it for?
Use it to run an improvement cycle, execute sprint work, check autonomy status, or stop ongoing automation through local or cloud workflows.
Why use it?
It keeps autonomous work bounded and traceable by recording runbooks and journals and by checking whether the project is ready before proceeding.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is okuzpe/midas-harness's own configuration. It tells Claude Code and Codex how to work on midas-harness 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 midas-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to okuzpe/midas-harness. 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/okuzpe/midas-harness/main/.agents/skills/midas-auto-pilot/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/okuzpe/midas-harness

Made for: Claude Code, Codex.

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 midas-auto-pilot

README.md
[![agentmods](https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-auto-pilot/github.svg)](https://agentmods.dev/skills/okuzpe/midas-harness/midas-auto-pilot)
Your own site
<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-auto-pilot"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-auto-pilot/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.

agentmods 80×15 button for midas-auto-pilot

Your own site · 80×15
<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-auto-pilot"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-auto-pilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,923 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 $0.00067 $0.02923
Opus 5 $0.00034 $0.01461
Sonnet 5 $0.00013 $0.00585
Haiku 4.5 $0.00007 $0.00292

Measured 5d ago against content hash 228831c93258, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

midas-auto-pilot 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.

.agents/skills/midas-auto-pilot/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

midas-auto-pilot — directed loop

Guard: <paths.engine>/templates/skill-state-ritual.md + AGENTS.md § Safety. Tick law (canonical): {runs}/auto-pilot/runbook.md ← template auto-pilot-runbook.md.tmpl. Wakes execute the runbook only — not this skill from the top (no B00 / delivery Ask). Artifacts: journal auto-pilot-journal.md, ticks auto-pilot-tick.md, playbook auto-pilot-cycle.md. ADR-009 CLI (L3): ./sprint-checklist.md.harness/autonomy/bin/midas-autopilot.mjs — never auto-tick from chat. Command map: docs/skills.md § Autonomy commands (install: <paths.engine>/docs/skills.md).

Response shape (always)

Keep the reply ≤8 lines (≤6 when intent + delivery known). No autonomy lecture unless asked.

  1. Verdictready | ready_with_warnings | blocked | stopped + short why
  2. Intentdirected | sprints | stop | status | unset (delivery Ask pending)
  3. Deliverypr | code | unset | n/a (non-loop)
  4. Modelocal | cloud | stop | n/a
  5. Next — one line
  6. Evidence — runbook / journal / tick-NN and/or CLI paths; tick result when a tick ran

When NOT

  • No install / no paths.state/midas-reconcile or install (INSTALL.md).
  • No planned candidate (sprint code line, failing feature, existing OPEN, existing sweep) → blocked; /plan-sprints or /start-sprint or /midas-adopt. idea.md alone is not enough.
  • ADR-009 CLI without .harness/autonomy/--autonomy via /midas-init (args setup / dry-run / tick / resume only).
  • Phase-8 gate verdict → /close-sprint.
  • Laptop will sleep / Cursor will quit → cloud mode; local /loop dies with the session.

Host /loop capability

Host Directed loop
Cursor Arm /loop (this skill).
Claude Code, Copilot, Windsurf, Gemini No Cursor /loop. Document the tick; the human re-invokes /midas-auto-pilot or uses cloud Automations.

Arguments (short-circuit)

Read the full file on GitHub · 171 lines

Files

What ships with it

1 file 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.

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. 5d ago Changed · -1 lines · +17 tokens per session 228831c93258
  2. 10d ago First seen · 172 lines · 50 tokens per session scan A ccbc777ceff2

Subscribe to this mod's changes

midas-auto-pilot is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 67 tokens to every session and 2,923 once invoked, about $0.0003 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 skills, from other repositories

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

projects

List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.

me2resh/apexyard · 24 tokens