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/c4al/codexcliplus/agents-mdgit clone --depth 1 https://github.com/C4AL/CodexCliPlusWhat 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 | $0.00172 | $0.00172 |
| Opus 5 | $0.00086 | $0.00086 |
| Sonnet 5 | $0.00034 | $0.00034 |
| Haiku 4.5 | $0.00017 | $0.00017 |
Grade A, and why
CodexCliPlus 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 yesterday.
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
Repository Rules
- Do not modify README files or change user-facing desktop UI language unless explicitly requested; desktop UI text must remain Chinese-only.
- Use Git identity
C4AL <[email protected]>for commits, and write commit summaries/bodies in concise Chinese. - Only commit, push, create releases, or push Git tags when explicitly requested, unless the task clearly requires repository synchronization.
- Before editing or committing, inspect
git statusand relevant diffs. - Stage and commit only current-task files; if unrelated or ambiguous dirty files may be overwritten, staged, reformatted, or regenerated, stop and ask first.
- When using PowerShell with Chinese input/output or file content, force UTF-8 first to avoid mojibake before editing or validating text.
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.
- yesterday First seen · 10 lines · 172 tokens per session scan A 6520b814ab16
CodexCliPlus AGENTS.md is an instructions file published in the GitHub repository C4AL/CodexCliPlus (10 stars, last pushed 3mo ago), licensed MIT. It adds 172 tokens to every session, about $0.0009 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
codex-usage-widget AGENTS.md
Instructions for ognjeeen/codex-usage-widget, covering agents.md, project, scope and decision discipline, authorization and repository safety and architecture boundaries.
codex-usage-widget CLAUDE.md
Instructions for ognjeeen/codex-usage-widget, a project described as: Local Windows widget for Codex subscription usage.
vibe-float AGENTS.md
Instructions for saheru/vibe-float, covering vibe float maintenance guide, repository map, required checks, windows startup contract and change discipline.
codexRS AGENTS.md
Instructions for Kiwunaka/codexRS, covering project rules, proportional engineering and universal safety.
apm python.instructions.md
Python development guidelines.
mcec AGENTS.md
Instructions for tig/mcec, covering agents.md: driving (and testing) mcec with an agent, the built-in guidance (single source of truth), security (do not regress), dogfood: test mcec using mcec (mcec drives mcec) and operational tips (learned the hard way).