Borrowing it
Nothing to install: this file belongs to masteryee-labs/Tool.Agent-Harness-Deploy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/masteryee-labs/Tool.Agent-Harness-Deploy/main/AGENTS.mdgit clone --depth 1 https://github.com/masteryee-labs/Tool.Agent-Harness-DeployWrote 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/masteryee-labs/tool.agent-harness-deploy/agents-md)<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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 | $0.46572 | $0.46572 |
| Opus 5.5 | $0.18629 | $0.18629 |
| Sonnet 5.5 | $0.09314 | $0.09314 |
| Haiku 4.5 | $0.04657 | $0.04657 |
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 1mo 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.
| **Skills loaded** | 10 | ≥1 skill deployed (auditor, gap-scan, etc.) | `ls .claude/skills/` or equivalent | 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 | 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 ---
- If the file does not exist, create an empty registry:
read(".agents/knowledge_distill.md")— load anti-patterns (<8KB).read(".agents/user_profile.md")— load profile (<2KB).- If
.agents/loop_state.mdhas anactive_sessionthat isin_progress,crashed, orsuspected_crashed,read(".agents/session_state/<session_id>.json")and.agents/loop_state/<session_id>.mdonly for audit. Do not read allsession_state/*.jsonorloop_state/*.mdfiles. If the previous session'sowned_files/affected_files/tagsoverlap the new task, ask the human whether to continue. Never auto-resume. - Read per-session context flags —
.agents/context_flags/<session_id>.jsonif 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.pyto update.agents/loop_state.mdregistry. - Read
Docs/02-Deployment-Guide.md— the exact deploy flow. - Run the deployer:
python scripts/distill.py(or followDocs/02-Deployment-Guide.md §Manual deploy).
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.
- 1mo ago First seen · 2,884 lines · 46,572 tokens per session scan D 17777b9ffb6d
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 3mo ago), licensed MIT. It adds 46,572 tokens to every session, about $0.1863 per session on Opus 5.5. 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).