A change-follow-up check for Midas projects that maps edits to the other files and generated outputs they may affect. A propagation check means verifying that related adapters, bundles, versions, documentation, and tests stay consistent.

Use it after changing skills, rules, conventions, installers, version files, or generated source trees to identify required follow-up work and run appropriate checks.

It helps catch incomplete changes before a merge or sprint ends, such as updated source rules that were not reflected in generated files or documentation.

How okuzpe/midas-harness configures Claude Code and Codex

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-align/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-align.svg)](https://agentmods.dev/skills/okuzpe/midas-harness/midas-align)

Your own site

<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-align"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-align.svg" alt="Measured on agentmods" height="20"></a>

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,355 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.

Model	Per session	Once invoked
Fable 5.1	$0.00090	$0.01355
Opus 5	$0.00045	$0.00678
Sonnet 5	$0.00018	$0.00271
Haiku 4.5	$0.00009	$0.00136

Measured 7d ago against content hash ac1a5edefe5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

midas-align 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 7d 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-align/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

midas-align — keep sources, bundles, docs, and versions aligned

Guard + state: <paths.engine>/templates/skill-state-ritual.md (+ AGENTS.md § Safety / Path resolution). Full matrix: <paths.engine>/rules/change-propagation.md. Tally: <paths.engine>/templates/audit-checklists.md.

Runs the propagation alignment pass so a change does not leave generated adapters, distribution bundles, version stamps, or user-facing docs behind. /midas-doctor covers adapter drift and install health; /midas-align adds the full matrix from change-propagation.md and a single gap report.

Detect context

Resolve --scope (default auto):

Signal	Scope
`scripts/test.mjs` exists at repo root and mentions `midas test`	engine (midas-harness contributor tree)
Otherwise	product (installed Midas project)

Procedure

1. Inventory what changed

Read git diff --name-only (or the paths the user names). Map each file to row(s) in <paths.engine>/rules/change-propagation.md § Propagation matrix. List required downstream actions before running anything.

2. Run the alignment ladder

Engine repo (midas-harness):

npm run align
# equivalent: node scripts/render-adapters.mjs && npm run verify

verify = test.mjs → build-plugin.mjs → build-create.mjs → doctor.mjs.

If --fix and adapters drifted: node scripts/render-adapters.mjs then re-run npm run verify.

Product install:

If <paths.engine>/conventions.md or <paths.engine>/rules/* changed → node <paths.scripts>/render-adapters.mjs or /midas-doctor --fix
Always → node <paths.scripts>/doctor.mjs
If product code changed → project test command (from architecture / AGENTS.md)
If harness/VERSION or midas_version semantics changed → /midas-init (tips pinned update; not in-place hand edits)

3. Version cascade (when `harness/VERSION` or release is in scope)

Engine repo: must run npm run bump -- <X.Y.Z> (change-propagation.md — never hand-scatter pins). That writes harness/VERSION only; scripts/sync-version.mjs propagates mirrors (also runs at the start of npm run build). Then confirm:

Read the full file on GitHub · 114 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.

7d ago First seen · 114 lines · 90 tokens per session scan A ac1a5edefe5f

Subscribe to this mod's changes

midas-align is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,355 once invoked, about $0.0005 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.

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

midas-harness: Skill for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

midas-align — keep sources, bundles, docs, and versions aligned

Detect context

Procedure

1. Inventory what changed

2. Run the alignment ladder

3. Version cascade (when `harness/VERSION` or release is in scope)

What this file has done since we first saw it

Other skills, from other repositories

systematic-debugging

local-ai-agents

next-cache-components-adoption

next-partial-prefetching-adoption

chronicle

babysit-pr

midas-harness: Skill for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

midas-align — keep sources, bundles, docs, and versions aligned

Detect context

Procedure

1. Inventory what changed

2. Run the alignment ladder

3. Version cascade (when harness/VERSION or release is in scope)

What this file has done since we first saw it

Other skills, from other repositories

systematic-debugging

local-ai-agents

next-cache-components-adoption

next-partial-prefetching-adoption

chronicle

babysit-pr

3. Version cascade (when `harness/VERSION` or release is in scope)