What is Tool.Agent-Harness-Deploy AGENTS.md?

Deployment instructions for an AI coding harness: a set of shared rules, memory, skills, and coordinating tools for coding agents. The repository is the installer that copies this harness into each supported coding tool's configuration.

Setting up the harness, checking session state, detecting installed coding tools, and synchronising their configuration.

They ensure the deployer is run in the required order and keep agents from mistakenly changing the installer instead of deploying the harness.

Tool.Agent-Harness-Deploy AGENTS.md — Instructions file for Codex and OpenCode by masteryee-labs: Deployment instructions for an AI coding h

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/masteryee-labs/tool.agent-harness-deploy/agents-md

Clone the repo

git clone --depth 1 https://github.com/masteryee-labs/Tool.Agent-Harness-Deploy

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/masteryee-labs/tool.agent-harness-deploy/agents-md.svg)](https://agentmods.dev/instructions/masteryee-labs/tool.agent-harness-deploy/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/masteryee-labs/tool.agent-harness-deploy/agents-md"><img src="https://agentmods.dev/badge/instructions/masteryee-labs/tool.agent-harness-deploy/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 46,572 This file is loaded in full into every session.

When invoked 46,572 The same file — it is already loaded in full.

Security scan D 3 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.

Model	Per session	Once invoked
Fable 5	$0.46572	$0.46572
Opus 5	$0.23286	$0.23286
Sonnet 5	$0.09314	$0.09314
Haiku 4.5	$0.04657	$0.04657

Measured 5d ago against content hash 17777b9ffb6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

Tool.Agent-Harness-Deploy AGENTS.md scanned grade D with 3 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| **Positive** | "About to run `rm -rf .agents/` — no .bak, no git tracking." |

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| 2 | Check CI → if failed: fix+push → if ok: wait | Multi-branch → `--branch`. Non-GitHub → `curl` API |

AGENTS.md · 2,884 lines

How it starts

The opening of the file, as written. The whole thing — 2,884 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Harness Deploy — Agent Entry File

You are reading this because an AI coding assistant cloned this repo after a user said "幫我部屬：[github link]" / "deploy: [github link]" / "set up this harness". This file is the single source of truth that every AGENTS.md-aware tool reads first.

0. What this repo is (read this before doing anything)

Agent Harness Deploy is a self-deploying, cross-tool AI harness deployer.

It does one job: detect which AI coding tools are installed on this machine, then generate and sync a single canonical harness (caveman-optimized, multi-agent, memory-enabled, loop-engineered, session-concurrent) into every detected tool's native config location — so that whichever tool the user opens next, they get the same rules, memory, skills, and orchestrator.

This repo is the deployer, not the product. The product is the harness it writes into your tools. Do not start building features. Do not refactor the deployer. Run the deployer.

1. BOOT protocol (order is mandatory)

read(".agents/loop_state.md") — read the session registry (<3KB).
- If the file does not exist, create an empty registry:
```
---
context_fill_pct: 0
caveman_level: full
active_sessions: []
active_session: null
---
```
read(".agents/knowledge_distill.md") — load anti-patterns (<8KB).
read(".agents/user_profile.md") — load profile (<2KB).
If .agents/loop_state.md has an active_session that is in_progress, crashed, or suspected_crashed, read(".agents/session_state/<session_id>.json") and .agents/loop_state/<session_id>.md only for audit. Do not read all session_state/*.json or loop_state/*.md files. If the previous session's owned_files/affected_files/tags overlap the new task, ask the human whether to continue. Never auto-resume.
Read per-session context flags — .agents/context_flags/<session_id>.json if it exists.
Output a GoalSpec (see distill/canon/BOOT_PROTOCOL.md) and write it to:
- .agents/loop_state/<session_id>.md
- .agents/session_state/<session_id>.json
Call python scripts/loop_memory_sync.py to update .agents/loop_state.md registry.
Read Docs/02-Deployment-Guide.md — the exact deploy flow.
Run the deployer: python scripts/distill.py (or follow Docs/02-Deployment-Guide.md §Manual deploy).

Read the full file on GitHub · 2,884 lines

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.

5d ago First seen · 2,884 lines · 46,572 tokens per session scan D 17777b9ffb6d

Subscribe to this mod's changes

Tool.Agent-Harness-Deploy AGENTS.md is an instructions file published in the GitHub repository masteryee-labs/Tool.Agent-Harness-Deploy (5 stars, last pushed 1mo ago), licensed MIT. It adds 46,572 tokens to every session, about $0.2329 per session on Opus 5. A static security scan graded it D with 3 findings (enumerates other installed skills, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents DevOps and cloud agent-harness agent-memory agentic agents-md ai-agent ai-coding-assistant

Tool.Agent-Harness-Deploy AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade D, and why

Enumerates other installed skillsmediumAgent snooping

Recursive force deletehighDestructive command

Makes network callslowCapability

How it starts

Agent Harness Deploy — Agent Entry File

0. What this repo is (read this before doing anything)

1. BOOT protocol (order is mandatory)

What this file has done since we first saw it

Other instructions, from other repositories

agent-cli AGENTS.md

unit-tests-skills CLAUDE.md

unit-tests-skills AGENTS.md

vibecode-pro-max-kit AGENTS.md

awesome-harness-engineering AGENTS.md

awesome-harness-engineering CLAUDE.md