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/kewton/commandmate/agents-mdgit clone --depth 1 https://github.com/Kewton/CommandMateWhat 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 | $0.00588 | $0.00588 |
| Opus 5 | $0.00294 | $0.00294 |
| Sonnet 5 | $0.00118 | $0.00118 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
CommandMate 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 yesterday.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This document provides repository-level guidance for coding agents (including Codex) working in CommandMate.
Scope
- Applies to the entire repository.
- This file is the primary entry point for agent behavior in this repo.
- For detailed background and implementation history, refer to
README.md,docs/, andCLAUDE.md.
Project Context
- Project: CommandMate
- Stack: Next.js 14, TypeScript, Tailwind CSS, SQLite (
better-sqlite3) - Runtime: Node.js 22+
- Main areas:
src/app: App Router pages and API routessrc/lib: core business logic and utilitiessrc/components: UI componentstests/unit,tests/integration,tests/e2e: test suites
Working Principles
- Keep changes issue-focused and minimal.
- Preserve existing architecture and naming patterns.
- Prefer small, reviewable commits over large refactors.
- Do not introduce unrelated cleanups in the same change.
- If behavior changes, add or update tests in the same PR.
Coding Rules
- Use strict TypeScript types; avoid
anyunless unavoidable. - Reuse existing utilities in
src/libbefore adding new helpers. - Keep API validation explicit and defensive.
- Follow existing React/Next.js patterns in the touched module.
- Keep comments short and meaningful; avoid obvious comments.
Safety And Boundaries
- Do not perform destructive operations (
git reset --hard, broad file deletion) unless explicitly requested. - Do not overwrite user-authored files unexpectedly.
- Treat auth/security-related paths with extra care:
src/lib/auth.tssrc/middleware.tssrc/lib/env-sanitizer.tssrc/lib/ip-restriction.ts
Validation Checklist
Before finishing, run relevant checks for changed scope:
# unit tests
npm run test:unit
# integration tests when API/DB behavior changes
npm run test:integration
# lint when editing TS/React broadly
npm run lint
For small fixes, run targeted tests first, then expand only if needed.
Change Policy For Agent Docs
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.
- yesterday First seen · 81 lines · 588 tokens per session scan A c13ee401a391
CommandMate AGENTS.md is an instructions file published in the GitHub repository Kewton/CommandMate (39 stars, last pushed yesterday), licensed MIT. It adds 588 tokens to every session, about $0.0029 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
psmux AGENTS.md
Instructions for psmux/psmux, covering agent instructions and test isolation.
vscode-ext-tmux-worktree AGENTS.md
Instructions for kargnas/vscode-ext-tmux-worktree, covering ai agent guidelines, instruction, tested vs code, 1. codebase understanding and project structure.
remobi AGENTS.md
Instructions for connorads/remobi, covering remobi, architecture, stack, key commands and local development.
tws AGENTS.md
Instructions for ytaskiran/tws, covering agents.md, build & test, ci, workflow and ...edit, commit, push, gh pr create.
Multiplex AGENTS.md
Instructions for multiplex-term/Multiplex, covering build & test, build, unit tests — fast, no device i/o, architecture and reference docs — read before touching an area.
tws CLAUDE.md
Instructions for ytaskiran/tws: Project guidance for this repository is maintained in AGENTS.md. Follow that file for build, test, workflow, architecture, and comment conventions. This file remains as a compatibility entry point for tools that discover CLAUDE.md.