dev_harness AGENTS.md

dev_harness AGENTS.md is an instructions file for Codex, OpenCode from yuvhaim-gif/dev_harness. It costs 392 tokens per session, scanned A, original, MIT.

A task and safety specification for an experimental system that confines autonomous AI agents to approved repository boundaries. It defines the files, tests, contracts, and limits for each requested change.

In plain words
What is it for?
Use it to guide tasks such as adding a payments endpoint or improving database queries, including which files may change, which tests must pass, and how changes are labelled.
Why use it?
It reduces the risk of an agent editing unintended files or changing an agreed interface, while allowing repairs within explicitly defined limits.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/yuvhaim-gif/dev_harness/agents-md
Clone the repo
git clone --depth 1 https://github.com/yuvhaim-gif/dev_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 dev_harness AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yuvhaim-gif/dev_harness/agents-md.svg)](https://agentmods.dev/instructions/yuvhaim-gif/dev_harness/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/yuvhaim-gif/dev_harness/agents-md"><img src="https://agentmods.dev/badge/instructions/yuvhaim-gif/dev_harness/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 392 This file is loaded in full into every session.
When invoked 392 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00392 $0.00392
Opus 5 $0.00196 $0.00196
Sonnet 5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 5d ago against content hash 8f76ea1077ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev_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 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.md · 45 lines

What it actually says

schema_version: 1

tasks: add_payments_endpoint: description: > Add a POST /payments endpoint to the billing service. Accepts amount, currency, and user_id. Returns a transaction_id. mutation_mode: evolve # evolve = may edit spec_docs, tests, targets spec_docs: # OKF concept bundle (each has a non-empty 'type') - harness/example/docs/IMPLEMENTATION.md - harness/example/docs/API_SCHEMA.md - harness/example/docs/index.md - harness/example/docs/log.md contracts: # stable, hash-pinned (subset of spec_docs) - harness/example/docs/API_SCHEMA.md tests: - harness/example/tests/test_payments.py contract_tests: # tests that pin the contract (subset of tests) - harness/example/tests/test_payments.py targets: - harness/example/src/billing/routes.py - harness/example/src/billing/models.py locked_files: [] # AGENTS.md is ALWAYS locked implicitly commit_prefix: "feat" max_autorepair_attempts: 3 pr_labels: ["feature", "billing"]

optimise_query_layer: description: > Optimise the database query layer in harness/example/src/db/queries.py. Replace N+1 patterns with batch fetches. No API contract changes. mutation_mode: isolated # isolated = ONLY files in targets may change spec_docs: - harness/example/docs/IMPLEMENTATION.md tests: - harness/example/tests/test_queries.py targets: - harness/example/src/db/queries.py locked_files: - harness/example/docs/IMPLEMENTATION.md - harness/example/tests/test_queries.py commit_prefix: "perf" max_autorepair_attempts: 3 pr_labels: ["performance"]

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 First seen · 45 lines · 392 tokens per session scan A 8f76ea1077ad

Subscribe to this mod's changes

dev_harness AGENTS.md is an instructions file published in the GitHub repository yuvhaim-gif/dev_harness (2 stars, last pushed 1mo ago), licensed MIT. It adds 392 tokens to every session, about $0.0020 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 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.

vercel/next.js · 7,296 tokens

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

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

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