midas-harness: Skill for Claude Code

.agents/skills/define-conventions/SKILL.md

define-conventions is a skill for Claude Code, Codex from okuzpe/midas-harness. It costs 43 tokens per session (1,628 once invoked), scanned A, original, Apache-2.0.

A workflow for turning a software architecture document into specific rules, design guidance, work instructions, and checks that can be applied to a project.

In plain words
What is it for?
Use it after the architecture stage to define project rules, create enforcement tooling, record the stage decision, and update adapters for coding tools.
Why use it?
It makes architectural decisions concrete and checkable before regular development begins. It also stops when the required architecture documents or decision records are missing.

Skill for Claude CodeCodex

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

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/define-conventions/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 define-conventions

README.md
[![agentmods](https://agentmods.dev/badge/skills/okuzpe/midas-harness/define-conventions.svg)](https://agentmods.dev/skills/okuzpe/midas-harness/define-conventions)
Your own site
<a href="https://agentmods.dev/skills/okuzpe/midas-harness/define-conventions"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/define-conventions.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,628 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 $0.00043 $0.01628
Opus 5 $0.00022 $0.00814
Sonnet 5 $0.00009 $0.00326
Haiku 4.5 $0.00004 $0.00163

Measured 3d ago against content hash 0c43737afa39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

define-conventions 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 3d 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/define-conventions/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

define-conventions (Phase 5 — architecture-as-rules + design system)

Guard + state: <paths.engine>/templates/skill-state-ritual.md (+ AGENTS.md § Safety / Path resolution). Prompt tool: AskQuestion. On Claude Code, fall back to AskUserQuestion if AskQuestion is not wired. Read paths.state. Precondition: stage: tech_architecture passed (or architecture_rules resuming). Missing {product}/architecture.md or ADRs → stop.

Does / Does not

Does Does not
Encode arch into CHECKABLE <paths.rules>/* + design system Self-advance stage (orchestrator audits gate)
Scaffold enforcement + re-render adapters Hand-edit generated .cursor/rules/*, .windsurf/rules/*
Freeze gate verdict to {runs}/audits/gate-05.md on pass (seed: <paths.engine>/templates/gate-record.md) Block on /midas-tribunal (optional pre-rules-freeze checkpoint)

Keystone: vague rules weaken every Phase-8 audit. Orchestrate decides; build writes files. Full pipeline steps + artifact table: <paths.engine>/pipeline/5-architecture-rules.md.

When NOT

  • Architecture / ADRs missing → /choose-architecture.
  • Rules already frozen and you need a sprint plan → /plan-sprints (amend overlays via capture/ADR, not a silent re-freeze).
  • Adapter drift only → /midas-doctor (does not replace this keystone).

Anti-rationalization: “we’ll add CHECKs later” is a fail — every new rule ships with a CHECK line in this phase.

Inputs: paths.state, {product}/architecture.md, {product}/adr/ADR-*.md, <paths.engine>/conventions.md, <paths.engine>/rules/, <paths.rules>/, token files.

Procedure (summary — detail in pipeline doc)

1. CHECKABLE rules → <paths.rules>/

  • folder-structure.md (mandatory): canonical tree + import/boundary rules. Feature/module layouts encode Scope Rule (1 consumer = local, 2+ = shared) and screaming folder names (user jobs, not technical-layer top-level). Layered/hexagonal ADRs win on conflict — cite the ADR. Seed: <paths.engine>/templates/folder-structure.md.
  • Stack rules — Context7-verified at pinned version per <paths.engine>/rules/context7-usage.md; shape from <paths.engine>/templates/stack-rule.md. Cover canonical idiom + lint set (not naming-only). Each carries docs: <lib>@<version> via <tool>. Each has a CHECK line. Name lint plugins that mechanize them.
  • {product}/conventions.md — prose overrides only; never restate base.

Read the full file on GitHub · 85 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. 3d ago Changed · +1 lines 0c43737afa39
  2. 8d ago First seen · 84 lines · 43 tokens per session scan A d4980be3b579

Subscribe to this mod's changes

define-conventions is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,628 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-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 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