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/thiientv/godmode/agents-mdgit clone --depth 1 https://github.com/thiientv/godmodeWhat 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 | $0.00389 | $0.00389 |
| Opus 5 | $0.00195 | $0.00195 |
| Sonnet 5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
godmode 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.
What it actually says
Godmode contributor instructions
Godmode is a portable Agent Skills project. Read docs/architecture.md and
docs/research.md before changing the public catalog or its vocabulary.
Working rules
- Keep the public catalog intentional. A public skill must represent a coherent engineering responsibility or workflow, not a single technique. Familiar names are preferred when they accurately describe a distinct responsibility; combine only when the boundary is genuinely clearer.
- Use the Agent Skills format: every public skill is a directory containing a
SKILL.mdwith valid YAML frontmatter. Keep the body focused and move optional detail to one-level-deepreferences/files. - Write behavior from first principles. Do not copy implementation text, datasets, scripts, or proprietary material from reference projects.
- Keep local research checkouts outside the runtime and package inputs.
- Prefer standard-library validation and deterministic tests. Do not add a runtime dependency for routing when native skill discovery is sufficient. Domain helpers may be dependency-free scripts when they produce repeatable artifacts or audits.
- Every workflow must identify what it needs to inspect, what it may change, and what evidence is required before a completion claim.
- Keep descriptions precise enough to route adjacent tasks without making unrelated skills compete.
Verification
Run the complete local gate before reporting a change as complete:
python3 scripts/validate.py
python3 -m unittest discover -s tests -p 'test_*.py'
If a change affects a plugin manifest, also run the relevant native validator when the client is installed:
claude plugin validate .
Codex compatibility must be checked through its local plugin help and marketplace/plugin validation path when that client exposes one. Do not claim that an agent loaded a skill unless a real session or native validator proves it.
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 · 47 lines · 389 tokens per session scan A 7efe00f307c2
godmode AGENTS.md is an instructions file published in the GitHub repository thiientv/godmode (93 stars, last pushed 7d ago), licensed MIT. It adds 389 tokens to every session, about $0.0019 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
aider-desk AGENTS.md
AGENTS.md instructions for hotovo/aider-desk, covering agents.md, common commands, development, type checking and linting and formatting.
Meta_Kim CLAUDE.md
Instructions for KimYx0207/Meta_Kim, covering metakim for claude code, fast read, what this repository is, claude code's role and canonical vs runtime files.
crystal CLAUDE.md
Instructions for stravu/crystal, covering crystal - multi-session claude code manager, project overview, references, implementation status: ✅ complete and ✅ implemented features.
easy-cheese python.instructions.md
Instructions for paulnsorensen/easy-cheese, covering hard rules, what to flag and what not to flag.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.