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/sevenschulte/agentic-harness/agents-mdgit clone --depth 1 https://github.com/sevenschulte/agentic-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/sevenschulte/agentic-harness/agents-md)<a href="https://agentmods.dev/instructions/sevenschulte/agentic-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/sevenschulte/agentic-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 | $0.02076 | $0.02076 |
| Opus 5 | $0.01038 | $0.01038 |
| Sonnet 5 | $0.00415 | $0.00415 |
| Haiku 4.5 | $0.00208 | $0.00208 |
Grade A, and why
agentic-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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agentic-harness CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — How This System Works
Edit me. Every
<placeholder>below is a slot for your team's reality. Replace them all before you ship. The structure is what's portable; the contents are yours.
Identity
You are working inside <repo-name>, the codebase for <product or domain>.
The team is <team name or composition>. The primary maintainer is <name or handle>.
Communication is direct, terse, and code-first. Explain reasoning in 2–3 sentences;
expand only when asked.
Follow the conventions in .claude/rules/ at all times. Those rules win over your
training defaults when they conflict.
Stack
- Language(s):
<e.g. Go 1.22, TypeScript 5.4, Python 3.12> - Backend:
<framework or "n/a"> - Frontend:
<framework or "n/a"> - Database:
<engine + version, or "n/a"> - Test runners:
<go test, vitest, pytest, etc.> - CI:
<GitHub Actions, GitLab CI, etc.> - Deployment target:
<where this runs in production>
Architecture (one paragraph)
<2–3 sentences describing the shape of the system: monorepo vs polyrepo, what the main directories are, what talks to what, what's deployed where. Keep it short — this is orientation, not documentation.>
Repo layout
<repo-name>/
├── AGENTS.md # This file — identity & orientation (cross-tool standard)
├── CLAUDE.md # Mirror of AGENTS.md (kept in sync) for Claude Code
├── README.md # Human-facing intro
├── .claude/ # Harness layer (Claude Code paths — see README "Adapting to other runtimes")
│ ├── rules/ # Must-never / must-always (auto-loaded by Claude Code)
│ ├── skills/ # Callable workflows (SKILL.md — open standard, see agentskills.io)
│ ├── hooks/ # Lifecycle scripts referenced by .claude/settings.json
│ └── settings.json # Claude Code runtime config (wires hooks to events)
├── memory/ # Persistent knowledge between sessions
│ ├── MEMORY.md # Curated facts (always loaded)
│ ├── ACTIVE.md # Current work status (always loaded)
│ ├── projects/ # Per-project context (read on demand)
│ └── coding-standards/ # Per-language standards (lazy-load via README.md index)
├── cron/ # Scheduled agents (no human in the loop)
└── <your source dirs> # Replace with the real top-level directories
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.
- 3d ago First seen · 182 lines · 2,076 tokens per session scan A 9dd1271b93e9
agentic-harness AGENTS.md is an instructions file published in the GitHub repository sevenschulte/agentic-harness (2 stars, last pushed 4mo ago), licensed MIT. It adds 2,076 tokens to every session, about $0.0104 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
domain-experts AGENTS.md
AGENTS.md instructions for wonsukchoi/domain-experts, covering agent guide for this repo, what lives where, rules, release (npm) and known pitfalls.
domain-experts CLAUDE.md
Claude Code instructions for wonsukchoi/domain-experts, covering domain experts — session bootstrap, non-negotiables when adding or editing roles, dual-graph context policy, mandatory: always follow this order and token usage.
coding-agent-rules AGENTS.md
Instructions for cskwork/coding-agent-rules, covering ten commandments for coding agents, response & documentation style and repository rules.
coding-agent-rules CLAUDE.md
Instructions for cskwork/coding-agent-rules, covering ten commandments for coding agents, response & documentation style and repository rules.
LynxPrompt CLAUDE.md
Claude Code instructions for GeiserX/LynxPrompt, covering claude.md - ai agent instructions for lynxprompt, 🚀 release process (critical - read carefully), understanding the release pipeline, step-by-step release process and 1. switch to develop branch.
pixeltamer-gpt-image-skill CLAUDE.md
Instructions for gabelul/pixeltamer-gpt-image-skill, covering claude.md — pixeltamer, what this is, architecture, how the skill works and the two backends.