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/0marm0/coord-harness/claude-mdgit clone --depth 1 https://github.com/0marm0/COORD-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/0marm0/coord-harness/claude-md)<a href="https://agentmods.dev/instructions/0marm0/coord-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/0marm0/coord-harness/claude-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 | $0.00731 | $0.00731 |
| Opus 5 | $0.00365 | $0.00365 |
| Sonnet 5 | $0.00146 | $0.00146 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
COORD-Harness CLAUDE.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 today.
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.
This is a copy
94% identical to COORD-Harness AGENTS.md — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoordHarness Claude entrypoint
COORDHARNESS_AGENT_INSTRUCTION_SENTINEL=v1
CoordHarness coordinates multi-agent work through one local SQLite authority. coord.db
owns work, claims, leases, handoffs, and lifecycle events. Markdown provides stable
orientation only; dashboards, job sidecars, knowledge.db, facts, KFTS, and accepted
memory are evidence or recall, never lifecycle state.
Start and finish
- If
.venv/bin/coordis missing, run./scripts/setup.sh, then restart this session — the checked-in MCP launcher (scripts/coord-mcp-launch.sh) fails closed with that same instruction instead of a raw ENOENT. Setup is done when.venv/bin/coord doctorexits0,.venv/bin/coord onboardreportsPASS, and MCPpreflightreturnsquery_core.mode="generic_coord_db"(docs/agent-onboarding.md§5, "Use the bounded MCP reads"). - Use the
operating-coordharnessrepo skill at.claude/skills/operating-coordharness/, and the packaged commands in.claude/commands/, invoked as/coord-start. - Run
coord-start: it fixes one stable session identity, runs.venv/bin/coord onboardonce, then MCPpreflight. If the board is empty, use.venv/bin/coord createwith a concrete repository-relativedone_signal. - Expand with bounded
board,next_work, andwork_contextreads. Use the context lenses only when the active row needs broader history or source evidence. - Claim before substantive work (
coord-claim): check the row'sdone_signaland acceptance first, then renew only near lease expiry or a material milestone. - Close with
coord-close: complete only after the declared proof passes, otherwise park, block, or release with a resume contract.coord-handoffmoves responsibility with exact row fences;coord-recoverreconciles a row the board is wrong about.
Do not edit SQLite or lifecycle projections by hand. Preserve unrelated dirty work and never weaken identity, proof, review, or authority checks to make a transition pass.
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.
- today Changed · +17 lines · +277 tokens per session f8ee364c3f35
- 4d ago First seen · 39 lines · 454 tokens per session scan A bfdf6d642c05
COORD-Harness CLAUDE.md is an instructions file published in the GitHub repository 0marm0/COORD-Harness (1 stars, last pushed today), licensed MIT. It adds 731 tokens to every session, about $0.0037 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to COORD-Harness AGENTS.md, differing in 12 lines, and is treated as a copy.
Other instructions, from other repositories
swarm-357 CLAUDE.md
Instructions for TechTideOhio/swarm-357, covering claude.md, what this repo is, python package (packages/techtide-swarm/), or from pypi and key classes.
kungfu CLAUDE.md
Claude Code instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before working in this repository. It routes both product use and contribution work to the repository sources of truth, including the requirement that development and build tasks enter through Shifu.
warren AGENTS.md
AGENTS.md instructions for jayminwest/warren, covering agents.md, what this project is, runtime topology, the burrow absorption (plan pl-3007) and per-project config (.warren/config.yaml).
BuildersGate CLAUDE.md
Claude Code instructions for Thepizzapie/BuildersGate, covering setting up builders gate for a user, ask two things first, install, point it at a game and keys.
VisionClaw-Agent-Public-Release AGENTS.md
AGENTS.md instructions for Huskyauto/VisionClaw-Agent-Public-Release, covering agents.md — working in the visionclaw codebase, identity, the cardinal discipline: search before reading, hard rules (non-negotiable) and architecture map (entrypoints).
open-bridge AGENTS.md
Instructions for bks-lab/open-bridge, covering the bridge — agent instructions, required reading, session start detection (automatic), theme and agents.