midas-harness: Instructions file for Codex

AGENTS.md

midas-harness AGENTS.md is an instructions file for Codex, OpenCode from okuzpe/midas-harness. It costs 2,135 tokens per session, scanned A, original, Apache-2.0.

A project instruction file for coding agents working on the Midas-harness repository, covering its purpose, conventions, file paths, and method for capturing recurring patterns.

In plain words
What is it for?
It helps agents follow project conventions, resolve paths, update harness guidance, and understand the repository’s software lifecycle tooling.
Why use it?
It gives agents the repository’s rules and boundaries so they do not treat the engine project like a generated product project.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is okuzpe/midas-harness's own configuration. It tells Codex and OpenCode 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.md
Clone the repo
git clone --depth 1 https://github.com/okuzpe/midas-harness

Made for: Codex, OpenCode.

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-harness AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/okuzpe/midas-harness/agents-md.svg)](https://agentmods.dev/instructions/okuzpe/midas-harness/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/okuzpe/midas-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/okuzpe/midas-harness/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,135 This file is loaded in full into every session.
When invoked 2,135 The same file — it is already loaded in full.
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 $0.02135 $0.02135
Opus 5 $0.01068 $0.01068
Sonnet 5 $0.00427 $0.00427
Haiku 4.5 $0.00214 $0.00214

Measured 2d ago against content hash b0776af1786c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

midas-harness AGENTS.md 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.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — harness

This file is project law for any AI agent working in this repository (Claude Code, Cursor, Copilot, Codex, Windsurf, …). It is engine-repo only (manually curated; ADR-005). Product installs get a different AGENTS.md from harness/templates/AGENTS.md.tmplcli/template/AGENTS.md at install time. Edit harness/conventions.md and re-run /midas-doctor to propagate adapter changes — this summary file is updated manually when engine metadata changes.

What this project is

Midas-harness is the engine repository for the Midas methodology — a copy-in kit of skills, rules, slash-commands, and agent definitions that drives software products from idea to shipped code through 9 audited phases. This repo authors that methodology in harness/ — it does not run the lifecycle on itself (see docs/dogfood.md). Never run create-midas install/update against this root (see harness/rules/engine-repo-boundary.md).

  • Stack: Node ESM scripts + MkDocs (engine tooling); product stacks are chosen per install in Phase 4
  • AI tools wired: claude-code, cursor, windsurf, gemini
  • Methodology: harness/methodology.md (9 audited phases, idea → shipped)
  • State: harness/state.yaml (contributor metadata — version, routing, path overrides)
  • Trace cache: runs/cache/ (gitignored); lifecycle CI fixture: scripts/fixtures/product-closed/

Conventions (always-on)

All rules in harness/conventions.md apply unconditionally. Key points:

  • Code quality — match surrounding code; prefer reuse over new abstractions; no dead code.
  • Naming — kebab-case files, PascalCase types, per-language idiom for functions/vars.
  • Errors — validate at boundaries; fail fast with actionable messages; never swallow errors.
  • Testing — every behaviour change ships with a test; test behaviour, not implementation.
  • Dependencies — justify before adding; pin versions; fetch current docs (Context7 or your own tool) before any third-party code.
  • Git — Conventional Commits (feat: fix: docs: refactor: test: chore:); small reviewable commits.
  • Engine releases (this repo) — publish / bump versions only with npm run bump -- <X.Y.Z> (harness/rules/change-propagation.md + VERSIONING.md). Do not hand-edit version pins across the tree.
  • Security — secrets only in ${ENV_VAR}; never commit them; least-privilege MCP scopes.
  • Design system — all UI uses {product}/design-system.md tokens; never hardcode colour/spacing/type.
  • Skills portabilityharness/skills/ is the editable source; .claude/skills, .agents/skills, and .cursor/skills are generated mirrors (npm run build) for host discovery (Claude / Codex / Cursor / Gemini). Never hand-edit the mirrors.

Read the full file on GitHub · 122 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 First seen · 122 lines · 2,135 tokens per session scan A b0776af1786c

Subscribe to this mod's changes

midas-harness AGENTS.md is an instructions file published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,135 tokens to every session, about $0.0107 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 2026-09-05.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens