midas-harness: Skill for Claude Code

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

midas-reconcile is a skill for Claude Code, Codex from okuzpe/midas-harness. It costs 73 tokens per session (1,089 once invoked), scanned A, original, Apache-2.0.

A read-only diagnostic guide for Midas, a project harness that manages installation and development stages.

In plain words
What is it for?
Use it after an update failure or when deciding whether to install, initialize, adopt, update, or check Midas.
Why use it?
It identifies whether Midas is missing, unfinished, outdated, or being run from the wrong folder, so you do not have to guess the next command.

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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node cli/install-diagnose.mjs <product-root>.

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-reconcile/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-reconcile

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-reconcile"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-reconcile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,089 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 $0.00073 $0.01089
Opus 5 $0.00036 $0.00544
Sonnet 5 $0.00015 $0.00218
Haiku 4.5 $0.00007 $0.00109

Measured 5d ago against content hash 1cb523213f4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

midas-reconcile 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-reconcile/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

midas-reconcile — which command should I run next?

Paths / state: <paths.engine>/templates/skill-state-ritual.md (read-only) + AGENTS.md § Path resolution.

Read-only. Never installs, never updates, never advances stage. Prints the one next step from the diagnose CLI — do not re-implement detection in the model.

Use when:

  • npx ... update failed with "no existing Midas install"
  • You are not sure whether to run /midas-init or /midas-adopt
  • You might be in a subfolder instead of the project root

Procedure

1. Run diagnose (source of truth)

If <paths.scripts>/install-diagnose.mjs exists as a file:

node <paths.scripts>/install-diagnose.mjs
# or machine-readable:
npx github:okuzpe/midas-harness --diagnose --json

Canonical v2 install: node .harness/scripts/install-diagnose.mjs

If that file is missing (engine sandbox seed, or paths.scripts points at repo scripts/):

# engine repo:
node cli/install-diagnose.mjs <product-root>
# otherwise:
npx github:okuzpe/midas-harness --diagnose

Do not assume paths.scripts existing as a directory means install-diagnose.mjs is there.

Run from the project root (or pass the path as the first argument).

2. Present the output verbatim

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

Do not invent a different command unless the script is missing (fallback below).

3. Fallback (script missing — manual read)

Observation Next step
No .harness/engine/VERSION, harness/VERSION, or .midas/engine/VERSION npx github:okuzpe/midas-harness#v{VERSION} --tools=cursor then /midas-init
.harness/product or state.yaml without .harness/engine/VERSION /midas-init (partial_migrate) — do not treat as a fresh install
Engine present and .harness/cache/installer/active.json exists npx … update --resume (or --rollback) — installer_incomplete
harness/VERSION or .midas/engine/VERSION exists but canonical engine does not Pin [email protected], migrate to .harness/, then upgrade to 3.x. 3.x refuses 1.x trees.
Engine present, setup_complete: false /midas-init
v2 midas_version ≠ engine VERSION Same: npx …#v{VERSION} update --yes (or /midas-init for the tip)
Parent dir has Midas, this folder does not cd to parent; /midas-status
Otherwise /midas-status

Read the full file on GitHub · 88 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. 5d ago Changed · +1 lines 1cb523213f4a
  2. 10d ago First seen · 87 lines · 73 tokens per session scan A c12ce25b8964

Subscribe to this mod's changes

midas-reconcile is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,089 once invoked, about $0.0004 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

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens