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/wholiver/metis/agents-mdgit clone --depth 1 https://github.com/Wholiver/metisWrote 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/wholiver/metis/agents-md)<a href="https://agentmods.dev/instructions/wholiver/metis/agents-md"><img src="https://agentmods.dev/badge/instructions/wholiver/metis/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 | $0.01499 | $0.01499 |
| Opus 5 | $0.00749 | $0.00749 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
metis 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 4d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Development Guide
This file is for AI coding agents contributing to Metis. Treat it as repository-level operating guidance. User and system instructions always take precedence.
Objective
Help developers change Metis quickly without sacrificing scope control, compatibility, or verification. Prefer evidence from the repository over assumptions.
Start Every Task
- Restate the requested outcome and concrete acceptance criteria.
- Read
git statusand preserve unrelated user changes. - Search for relevant code, tests, docs, and existing abstractions before editing.
- Read the nearest applicable
AGENTS.mdif a nested one exists. - Identify affected modes: TUI, print, JSON, RPC, SDK, Extensions, Packages.
- Decide the smallest validation set that can prove the change works.
If .codegraph/ exists and its tools work, use CodeGraph before broad text search for code understanding. If the index is missing or malformed, state that once and fall back to rg and targeted file reads.
Repository Map
| Area | Primary paths |
|---|---|
| CLI entry and mode selection | src/main.ts, src/cli/, src/modes/ |
| Agent session and SDK | src/core/agent-session.ts, src/core/agent-session-runtime.ts, src/core/sdk.ts |
| Built-in model tools | src/core/tools/ |
| Extensions | src/core/extensions/, docs/extensions.md, examples/extensions/ |
| Package loading | src/core/package-manager.ts, docs/packages.md |
| Dream and built-ins | src/core/builtins/ |
| TUI | src/modes/interactive/, vendor/metis-tui/ |
| Desktop frontend | desktop/, docs/desktop-frontend-development.md |
| RPC | src/modes/rpc/, src/rpc-entry.ts |
| Public exports | src/index.ts |
| Tests | test/, vitest.config.ts |
| User documentation | README.md, README.zh-CN.md, docs/ |
Do not modify vendor/ unless the requested behavior belongs to a vendored package. Do not edit generated dist/ output by hand.
Desktop Frontend Changes (Mandatory)
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.
- 4d ago First seen · 131 lines · 1,499 tokens per session scan A 02f62f3fa626
metis AGENTS.md is an instructions file published in the GitHub repository Wholiver/metis (133 stars, last pushed 2d ago), licensed MIT. It adds 1,499 tokens to every session, about $0.0075 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 2026-08-30.
Other instructions, from other repositories
mavericks-os CLAUDE.md
Claude Code instructions for yahor-punko/mavericks-os, covering claude.md, what this repo is, session start, operational commands and architecture.
cctop AGENTS.md
AGENTS.md instructions for st0012/cctop, covering agents.md - development guide for cctop, scope and sources, required development rules, driver workflow and github and pr rules.
babysitter CLAUDE.md
Claude Code instructions for a5c-ai/babysitter, covering claude.md, repo-specific overrides, read these first, quick commands and claude code local notes.
omk CLAUDE.md
Claude Code instructions for dmae97/omk, covering claude.md, precedence (read this first), omk runtime map (what you're operating inside), this repo: open-multi-agent-kit / omk monorepo and build / test / check commands.
david-vscode CLAUDE.md
Instructions for edwardyen724-g/david-vscode, covering claude.md, project: david — agent orchestration for claude code, build, package, install, produce a .vsix and local install.
dev-3.0 CLAUDE.md
Claude Code instructions for h0x91b/dev-3.0, a project described as: Mission control for the One Person Studio — run a fleet of AI coding agents in parallel without losing your mind. Kanban + git worktrees + tmux for Claude Code, Codex, Gemini CLI, OpenCode and any shell agent. Not an IDE.