midas-harness: Skill for Claude Code

.agents/skills/midas-init/SKILL.md

midas-init is a skill for Claude Code, Codex from okuzpe/midas-harness. It costs 49 tokens per session (1,368 once invoked), scanned A, original, Apache-2.0.

An onboarding command for diagnosing a project’s installation, setup, and engine version, then choosing the appropriate next step. It can guide installation or updates and run a one-time setup process, including for a monorepo—a repository containing several related projects.

In plain words
What is it for?
Use it when starting a project, when setup is incomplete, when the tool version is outdated, or when diagnosing whether the engine is installed correctly.
Why use it?
It gives a project a single entry point for setup and avoids guessing which installation or update action is needed. It also handles special setup modes such as monorepos and dry runs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: 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-init/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-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-init.svg)](https://agentmods.dev/skills/okuzpe/midas-harness/midas-init)
Your own site
<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-init"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,368 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 $0.00049 $0.01368
Opus 5 $0.00024 $0.00684
Sonnet 5 $0.00010 $0.00274
Haiku 4.5 $0.00005 $0.00137

Measured 2d ago against content hash 5b764385cdf8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

midas-init 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 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.

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-init/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

midas-init — install / setup / update tip

Guard + state: <paths.engine>/templates/skill-state-ritual.md (+ AGENTS.md § Safety / Path resolution). Surface: primary — single human entry for onboarding. SoT for install shape: node <paths.scripts>/install-diagnose.mjs when that file exists (or npx github:okuzpe/midas-harness --diagnose). Do not re-implement detection in the model.

One slash: detect where the project is, then tip the install CLI, run one-time setup, or tip a pinned update.

Does / Does not

Does Does not
Run diagnose and branch on status Invent a parallel install/update plan
Run adaptive intake when setup_pending Run intake when not installed (no engine on disk)
Tip exact CLI for install or update Run npx update without the human typing it
Honor --monorepo / --dry-run on intake path Replace /midas-reconcile (read-only “which command?”)
Honor track: lite per <paths.engine>/pipeline/lite.md (Phase D Ask) Skip {product}/business-plan.md on lite — write a thin stub; {product}/market.md is the optional skip

Procedure

0. Diagnose (always)

# if <paths.scripts>/install-diagnose.mjs exists:
node <paths.scripts>/install-diagnose.mjs
# else:
npx github:okuzpe/midas-harness --diagnose

Statuses: not_installed | unsupported_v1 | setup_pending | version_behind | nested_or_wrong_cwd | partial_migrate | installer_incomplete | ready

1. Branch (exact)

Status Action
not_installed Print diagnose nextCli (install, never update). Say: Install first, then re-run /midas-init. STOP — do not start intake.
setup_pending Continue to § Intake below (init-adaptive A–F). Forward --monorepo / --dry-run.
version_behind Print diagnose nextCli (pinned update). Optionally mention dry-run. Allowed even when setup_complete: true. Do not invent a copy plan. STOP after the tip.
unsupported_v1 Print diagnose nextCli (pin [email protected], migrate, then upgrade to 3.x). STOP. Do not run 3.x update — it writes nothing.
partial_migrate Print diagnose nextCli (rollback if a journal exists) and the recover+update detail. STOP. Do not start intake or a fresh install unless the human intends to discard leftover .harness/product.
installer_incomplete Print diagnose nextCli (update --resume) and the --rollback detail. STOP. Do not start intake or a new update until that run is cleared.
nested_or_wrong_cwd Print detail; ask human to cd to project root; STOP.
ready Onboarding complete — 👉 Run /midas-status. If args include --monorepo, run Phase F only (see init-adaptive); do not flip setup_complete. Otherwise STOP.

Read the full file on GitHub · 90 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 Changed · +1 lines 5b764385cdf8
  2. 7d ago First seen · 89 lines · 49 tokens per session scan A c3553587ff84

Subscribe to this mod's changes

midas-init is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,368 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens