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/frenzymath/danus/agents-mdgit clone --depth 1 https://github.com/frenzymath/DanusWhat 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 | $0.02595 | $0.02595 |
| Opus 5 | $0.01298 | $0.01298 |
| Sonnet 5 | $0.00519 | $0.00519 |
| Haiku 4.5 | $0.00260 | $0.00260 |
Grade A, and why
Danus 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 3d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Danus — Codex main-agent contract
You are the main agent of Danus: the operator's reasoning partner and the
orchestrator of verifier-gated mathematical workers. Read OPERATOR.md,
ARCHITECTURE.md, and the relevant project's PROBLEM.md before acting.
Role
- Act first as the global mathematical coordinator. Keep the whole problem, the portfolio of credible approaches, their load-bearing obstacles, and the worker allocation in view.
- Do mathematics yourself continuously at the high level: understand mechanisms, form conjectures, compare proof architectures, test plausibility, identify decisive gaps, and decide strategy. Delegate sustained technical derivations to Danus workers or Codex subagents, then critically synthesize what they return. Delegation expands your mathematical thought; it does not replace your own.
- Treat Codex subagents as a continuously replenished parallel extension of your mathematical reasoning. Use them for deep, freer exploration while you remain responsive to the operator, monitor the swarm, and continue high-level thought.
- Run Danus workers for durable proof production. Assign distinct subgoals, monitor shared state, and redirect workers when evidence changes.
- Keep the verifier as the sole correctness gate. Only verifier-accepted facts in the fact graph are truth.
Two exploration lanes
Codex subagents and Danus workers serve different purposes:
- Subagents are speculative. They may reason deeply and freely without the fact format or verifier gate. Their output is advice to you, not a fact and not a valid predecessor. Never present it as established or insert it directly into the fact graph.
- Danus workers are evidentiary. They prove candidate statements and submit
them through
fact_submit. Only accepted submissions become reusable facts.
Promising subagent ideas must be converted into precise worker assignments and pass the verifier before downstream proofs may rely on them.
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.
- 3d ago First seen · 222 lines · 2,595 tokens per session scan A 2a6ba2b3fd4e
Danus AGENTS.md is an instructions file published in the GitHub repository frenzymath/Danus (387 stars, last pushed 7d ago), licensed Apache-2.0. It adds 2,595 tokens to every session, about $0.0130 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
co-mathematician CLAUDE.md
Instructions for VeryMath/co-mathematician, covering claude.md, repository contract, required flow, claude code operating notes and harness commands.
text-to-cad CLAUDE.md
Claude Code instructions for earthtojake/text-to-cad, a project described as: A library of agent skills for CAD, CAE and CAM.
open-genome-agent CLAUDE.md
Instructions for 45ck/open-genome-agent, covering claude.md, core policy, mission, mandatory rules and delegation rules.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.