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/soju06/codex-lb/agents-mdgit clone --depth 1 https://github.com/Soju06/codex-lbWhat 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 | $0.01906 | $0.01906 |
| Opus 5 | $0.00953 | $0.00953 |
| Sonnet 5 | $0.00381 | $0.00381 |
| Haiku 4.5 | $0.00191 | $0.00191 |
Grade A, and why
codex-lb AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
Environment
- Python: .venv/bin/python (uv, CPython 3.13.3)
- GitHub auth for git/API is available via env vars:
GITHUB_USER,GITHUB_TOKEN(PAT). Do not hardcode or commit tokens. - For authenticated git over HTTPS in automation, use:
https://x-access-token:${GITHUB_TOKEN}@github.com/<owner>/<repo>.git
Code Conventions
The /project-conventions skill is auto-activated on code edits (PreToolUse guard).
| Convention | Location | When |
|---|---|---|
| Code Conventions (Full) | /project-conventions skill |
On code edit (auto-enforced) |
| Git Workflow | .agents/conventions/git-workflow.md |
Commit / PR |
Workflow (OpenSpec-first)
This repo uses OpenSpec as the primary workflow and SSOT for change-driven development.
How to work (default)
- Find the relevant spec(s) in
openspec/specs/**and treat them as source-of-truth. - If the work changes behavior, requirements, contracts, or schema: create an OpenSpec change in
openspec/changes/**first (proposal -> tasks). - Implement the tasks; keep code + specs in sync (update
spec.mdas needed). - Validate specs locally:
openspec validate --specs - When done: verify + archive the change (do not archive unverified changes).
Source of Truth
- Specs/Design/Tasks (SSOT):
openspec/- Active changes:
openspec/changes/<change>/ - Main specs:
openspec/specs/<capability>/spec.md - Archived changes:
openspec/changes/archive/YYYY-MM-DD-<change>/
- Active changes:
Documentation & Release Notes
- OpenSpec is the SSOT for feature/behavior documentation. User-facing rendering lives under
docs/(the published docs pages), and each spec-governed page MUST link back to the owningopenspec/specs/<capability>/entry. Do not createdocs/content that has no OpenSpec counterpart, and do not add feature docs as new README sections. Keep normative requirements inopenspec/specs/<capability>/spec.mdand free-form rationale in the capability'scontext.md(or change-level context underopenspec/changes/<change>/context.md). - Do not edit
CHANGELOG.mddirectly. Leave changelog updates to the release process; record change notes in OpenSpec artifacts instead.
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 · 140 lines · 1,906 tokens per session scan A 5d64b99feea3
codex-lb AGENTS.md is an instructions file published in the GitHub repository Soju06/codex-lb (2,907 stars, last pushed yesterday), licensed MIT. It adds 1,906 tokens to every session, about $0.0095 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
codexU AGENTS.md
Instructions for shanggqm/codexU, covering agents.md, 项目边界, 关键文档, 代码结构 and 项目级 skills.
mate CLAUDE.md
Instructions for antiv/mate, covering claude.md, project overview, running the application, setup and run (auto-applies db migrations, default sqlite).
AI-company CLAUDE.md
Instructions for CronusL-1141/AI-company, covering ai team os, 核心约束, leader核心行为, 多会话并行纪律（2026-07-10 事故后立规） and 刻意决策 — 禁止悄悄回退.
mate AGENTS.md
Instructions for antiv/mate, covering mate (multi-agent tree engine) system instructions, code style, development environment, architecture and server architecture.
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
Vibe-Research AGENTS.md
Instructions for simonlin1212/Vibe-Research, covering vibe-research-agent 金融研究宪法, 0. 三条不可越线, 1. 数据纪律(五问 gate:给出任何数字或结论前逐条自问), 2. 研究哲学(评估框架,不是预测工具) and 3. 估值口径(你只选输入、解释输出;计算交给 calc/).