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.
npx agentmods add instructions/samartomar/ai-harness/agents-mdgit clone --depth 1 https://github.com/samartomar/ai-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/samartomar/ai-harness/agents-md)<a href="https://agentmods.dev/instructions/samartomar/ai-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/samartomar/ai-harness/agents-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 | $0.00891 | $0.00891 |
| Opus 5 | $0.00445 | $0.00445 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
ai-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 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-harness — agent bootloader (AGENTS.md)
This file is not the full rulebook. It is the cross-tool entry point read by
Codex CLI, Antigravity, OpenCode, Zed, Kimi CLI, and Kiro; canonical guidance lives in
ai-coding/ (start at RULE_ROUTER.md). The shared block below is a manual
self-hosting mirror of ai-coding/adapters/_shared-canonical-block.md; AIH must
never regenerate it in this checkout.
Per-tool notes: ai-coding/adapters/.
Repo-specific tool routing: before non-trivial repository work, read
ai-coding/rules/repo-ai-tools.md. It overrides generic tool-selection guidance
in the shared block below.
Never run AIH against this checkout. Product behavior must use temporary fixture roots in tests; repository-owned direct development checks may inspect this tree.
Start here
Read ai-coding/RULE_ROUTER.md first — layered baseline+repo model, the detected
stack, and task routing. Load only task-relevant rules, then verify against repo
evidence (PR diff, files, tests, schemas, CI) — never model memory or local notes.
Full working discipline: ai-coding/rules/agent-behavior-core.md. Read it before
any non-trivial change; the essentials are inline below.
Self-hosting boundary
Never run AIH against this checkout. Do not invoke an installed aih, npx aih,
or src/cli.ts / dist/cli.js project command with this repository as its target,
including read-only setup or governance commands. Maintain the AI canon manually
under ai-coding/; exercise AIH product behavior only against temporary fixture
roots in tests. Repository-owned direct checks and version/help smoke tests remain
allowed because they do not apply AIH project behavior to this checkout.
Working agreement
- Think before coding — state the goal and the smallest change that meets it; surface tradeoffs, don't pick silently.
- Simplicity first — minimum code that solves it; nothing speculative.
- Surgical changes — touch only what the task needs; match the nearest peer file; every changed line traces to the request.
- Goal-driven — turn the task into a verifiable check (write the failing test first), then loop until it is green.
- Use the canon's tools — use the canonical tool this repo names; don't load MCP servers just-in-case; when two look alike, pick the one the canon names.
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 · 71 lines · 891 tokens per session scan A af2e2418e6d9
ai-harness AGENTS.md is an instructions file published in the GitHub repository samartomar/ai-harness (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 891 tokens to every session, about $0.0045 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
ReqForge CLAUDE.md
Instructions for zxpmail/ReqForge, a project described as: ReqForge — From requirements to shippable products. Open-source Agent Harness for Claude Code, Cursor & OpenCode. Spec→Plan→Build, hooks, review. /change-manager for brownfield.
RepoResident AGENTS.md
Instructions for ychamel/RepoResident: Agent entry point: read CLAUDE.md in full — it is the operating manual — then follow its Session protocol. Everything else (state, workflows, project knowledge) is routed from there via the .agent/ directory.
Oficina AGENTS.md
AGENTS.md instructions for JoaoEquer/Oficina: Entry point for harnesses that read AGENTS.md (Codex, Cursor, OpenCode, Gemini CLI and similar).
manor AGENTS.md
Instructions for peter-olom/manor, covering local development, agent judgment and hard boundaries, butler model providers and harnesses and content admission and runtime security.
tink-harness AGENTS.md
AGENTS.md instructions for dotoricode/tink-harness, covering tink-harness, 명령, 구조, 3-copy 규칙 and 버전 bump.
tink-harness CLAUDE.md
Claude Code instructions for dotoricode/tink-harness, covering tink-harness, 명령, 구조, 3-copy 규칙 and 버전 bump.