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 commands/pablomarin/claude-codex-forge/codexgit clone --depth 1 https://github.com/pablomarin/claude-codex-forgeWhat 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 | $0.00000 | $0.07478 |
| Opus 5 | $0.00000 | $0.03739 |
| Sonnet 5 | $0.00000 | $0.01496 |
| Haiku 4.5 | $0.00000 | $0.00748 |
Grade A, and why
codex 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 — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Second Opinion
Get a second opinion from OpenAI's Codex CLI. Use for code reviews, design plan reviews, architecture feedback, or general questions. For multi-perspective analysis with 5 advisors, use
/council <question>instead.
Prerequisites
- Codex CLI installed:
npm i -g @openai/codexorbrew install --cask codex - Codex authenticated:
codex login(requires ChatGPT Plus/Pro/Business or API key) - Verify:
codex --version(requires v0.124.0+ — every mode here captures the clean verdict with--output-last-message, stable since 0.124 per openai/codex#4644)
Use
.claude/hooks/lib/codex-pty.sh execfor all Codex invocations (Windows:.claude/hooks/lib/codex-pty.ps1 exec). Do not call barecodex execfrom Claude Code.
Mode Detection
Analyze $ARGUMENTS to determine the mode:
- Code Review Mode: Arguments match review-related keywords — "review code", "code review", "review changes", "review diff", "review PR", or bare "review"
- Design Review Mode: Arguments reference a plan, design, or architecture — "review the plan", "review the design", "review architecture"
- Investigate Mode: The task needs reach a hermetic sandbox denies — it requires ANY of: project credentials, network access, external systems (DB / cloud / API), live data, or non-hermetic execution. Detected by capability-need, not by guessing intent — e.g. "have Codex dig into the data", "give Codex DB access to find the cause", "let Codex actually run X against the live system". Check this BEFORE falling through to General.
- General Mode: Everything else (give opinion, analyze code, brainstorm, ask a question) — stays hermetic (read-only, no network)
Finding Triage — before you adopt Codex's findings
Codex biases toward robustness and edge cases. Before treating any Codex finding as must-fix (P0/P1/P2) and opening a revision-loop round (.claude/rules/workflow.md Revision Loop Protocol), apply this filter. It governs how severity gets assigned — once assigned, the loop protocol is unchanged: P0/P1/P2 still must be fixed before proceeding.
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 · 392 lines · 0 tokens per session scan A 96c711385bbe
codex is a command published in the GitHub repository pablomarin/claude-codex-forge (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,478 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.