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/octanevz/codex-debate/agents-mdgit clone --depth 1 https://github.com/octanevz/codex-debateWrote 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/octanevz/codex-debate/agents-md)<a href="https://agentmods.dev/instructions/octanevz/codex-debate/agents-md"><img src="https://agentmods.dev/badge/instructions/octanevz/codex-debate/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 5.1 | $0.00046 | $0.00046 |
| Opus 5 | $0.00023 | $0.00023 |
| Sonnet 5 | $0.00009 | $0.00009 |
| Haiku 4.5 | $0.00005 | $0.00005 |
Grade A, and why
codex-debate 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 5d 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
AGENTS.md
Contributor guidance for all coding agents in this repository lives in CLAUDE.md — read it and follow it; everything there applies to any agent, not just Claude Code.
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.
- 5d ago First seen · 4 lines · 46 tokens per session scan A cfeb2dfb39ba
codex-debate AGENTS.md is an instructions file published in the GitHub repository octanevz/codex-debate (2 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session, about $0.0002 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
OmniForge CLAUDE.md
Claude Code instructions for nexiouscaliver/OmniForge, covering claude.md, what this is, repository layout, commands and run tests.
river-review CLAUDE.md
Claude Code instructions for s977043/river-review, covering claude code project guide (river-review), decision policy, change policy, reporting and ai misoperation guards.
adversarial-review AGENTS.md
Instructions for robertoecf/adversarial-review, covering agents.md: review agent guidelines (host-agnostic), plugin architecture, cross-host routing, anti-recursion contract and critique discipline (v0.8.1+).
river-review copilot-instructions.md
Copilot instructions for s977043/river-review, covering copilot instructions (river-review), 必須チェック（着手前に確認）, 参照ポイント, 責務分離ルール（肥大化防止） and レイヤー別の使い分け.
river-review GEMINI.md
Gemini CLI instructions for s977043/river-review, covering gemini instructions (river-review), 必須チェック, gemini-specific tips, prompt assembly and development tips.
river-review skills.instructions.md
Instructions for s977043/river-review, covering instructions for skill documents, structure & schema, content guidelines, output format and style.