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/cvsloane/agent-commander/agents-mdgit clone --depth 1 https://github.com/cvsloane/agent-commanderWhat 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 | $0.00194 | $0.00194 |
| Opus 5 | $0.00097 | $0.00097 |
| Sonnet 5 | $0.00039 | $0.00039 |
| Haiku 4.5 | $0.00019 | $0.00019 |
Grade A, and why
agent-commander 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- mainwp-mcp AGENTS.md — 92% identical, 4 lines differ
What it actually says
AGENTS.md
Canonical cross-tool instructions for this repo.
Repository Overview
- Repo:
agent-command - Location:
/home/cvsloane/dev/agent-command - Treat this file as the concise always-loaded contract. Put long procedures in repo docs, skills, or SloaneVault.
Working Rules
- Read the repo before changing code; prefer existing patterns and commands.
- Keep changes scoped to the task and avoid unrelated refactors.
- Do not commit, deploy, delete data, rotate secrets, or run paid/bulk operations unless explicitly asked.
- Preserve user changes and generated work you did not create.
- Use SloaneVault/qmd for company context and durable documentation instead of pasting large context here.
Verification
- Run the narrowest command that proves the change works.
- If commands are unknown, inspect package/config files and document what you ran.
- Report any verification you could not run and why.
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.
- 2d ago First seen · 24 lines · 194 tokens per session scan A 1a8be7a3812c
agent-commander AGENTS.md is an instructions file published in the GitHub repository cvsloane/agent-commander (5 stars, last pushed 5d ago), licensed MIT. It adds 194 tokens to every session, about $0.0010 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 2026-08-31.
Other instructions, from other repositories
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
agents CLAUDE.md
Instructions for eloylp/agents, covering claude.md, project overview, directory structure, config model and build & run.
codevira CLAUDE.md
Instructions for sachinshelke/codevira, covering codevira — persistent project memory, when to call which codevira tool, at the start of every session, before modifying any file and before adopting a pattern, library, or naming convention.
hermes-model-auto-switch AGENTS.md
Instructions for rhishi99/hermes-model-auto-switch, covering install, verify, uninstall, guardrails and conventions.
growmos AGENTS.md
Instructions for codician-team/growmos: This repository keeps a knowledge graph in .growmos/ (entities, typed relations, provenance, profiles, a journal). It is the shared world model that survives context windows. Treat it as memory you read at the start of work and write to as you develop. Zero-config commands.