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.
curl -O https://raw.githubusercontent.com/okuzpe/midas-harness/main/GEMINI.mdgit clone --depth 1 https://github.com/okuzpe/midas-harnessWrote 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.
[](https://agentmods.dev/instructions/okuzpe/midas-harness/gemini-md)<a href="https://agentmods.dev/instructions/okuzpe/midas-harness/gemini-md"><img src="https://agentmods.dev/badge/instructions/okuzpe/midas-harness/gemini-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02461 | $0.02461 |
| Opus 5 | $0.01230 | $0.01230 |
| Sonnet 5 | $0.00492 | $0.00492 |
| Haiku 4.5 | $0.00246 | $0.00246 |
Grade A, and why
midas-harness GEMINI.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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project memory — Midas (Gemini CLI)
Generated by Midas from
harness/conventions.md. Do not hand-edit — run/midas-doctor(ornode scripts/render-adapters.mjs) to re-render.
Midas base conventions (always-on)
This file is the base body of project law. Its contents are inlined into generated tool adapters
and summarized in AGENTS.md. In installed projects it is vendor-owned and immutable: project
overrides belong in {product}/conventions.md or <paths.rules>/. Engine contributors edit this
source and run /midas-doctor; installed projects run /midas-doctor after changing their overlays.
Precedence (when rules conflict, higher wins)
project rule overlay (<paths.rules>/) > stack-specific rules > {product}/conventions.md > {product}/design-system.md > these base conventions
An overlay at <paths.rules>/<slug>.md wins over a base or stack rule with the same slug.
Stack-specific rules are generated during Phase 5 by /define-conventions (docs-verified for the
chosen framework). {product}/conventions.md and {product}/design-system.md are project overrides the
team owns. This base file is the floor every project starts from. There is exactly one taxonomy —
do not introduce a parallel "standards" layer.
Path resolution
Read layout and paths from paths.state. Pipeline and skills use tokens — substitute before I/O:
{runs}/→paths.runs(.harness/runs/){product}/→paths.product(.harness/product/)
Engine source: paths.engine (.harness/engine/). Project rule overlays: paths.rules
(.harness/rules/); an overlay wins over a base rule with the same slug.
Code quality
- Match the surrounding code: naming, structure, comment density, idioms. New code should be indistinguishable from existing code.
- Prefer reuse over new abstractions. Search for an existing utility before writing one.
- Functions do one thing; keep them small and named for their effect.
- No dead code, no commented-out blocks, no TODO without an owner/condition.
- Lean ladder before expanding code — need? → reuse → stdlib → native → installed dep → one
line → only then the minimum that works. Never cut trust-boundary validation, security, or
accessibility. Full rule:
rules/lean-ladder.md; delete-list review:/midas-lean-review.
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.
- 6d ago First seen · 164 lines · 2,461 tokens per session scan A 958833bd7f52
midas-harness GEMINI.md is an instructions file published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,461 tokens to every session, about $0.0123 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.
Other instructions, from other repositories
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.
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.
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).
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).
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.
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.