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/jgt87/codex-offload-mcp/codex-reviewgit clone --depth 1 https://github.com/jgt87/codex-offload-mcpWrote 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/commands/jgt87/codex-offload-mcp/codex-review)<a href="https://agentmods.dev/commands/jgt87/codex-offload-mcp/codex-review"><img src="https://agentmods.dev/badge/commands/jgt87/codex-offload-mcp/codex-review.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 | $0.00019 | $0.00384 |
| Opus 5 | $0.00010 | $0.00192 |
| Sonnet 5 | $0.00004 | $0.00077 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
codex-review 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 4d 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
The user wants the execute→review loop: Codex does the work, you check it.
Task: $ARGUMENTS
- Dispatch with
codex_start(prompt, cwd)— a self-contained prompt, since Codex cannot see this conversation. You get a jobId back immediately; keep working meanwhile. Don't sleep-poll — foregroundsleepis blocked by the harness, so a narrated wait collapses into an instant re-poll; do real work and collect withcodex_resultwhen ready, or run the returnedwatchCommandvia Bash withrun_in_backgroundfor a one-shot completion notification. Don't useMonitorfor this: it is for repeated events, not a single job-completion wait. Don't just say "I'll check back later" and end the turn either — nothing brings you back on its own, so that promise goes unfulfilled until the user re-prompts you; either armwatchCommandnow or keep working now. - Collect and review with
codex_result. TrustactualChanges(git's account) over Codex's own report, and re-read each changed file before judging it. Check correctness, not just that it ran. - Correct in place with
codex_reply(jobId, ...)— it keeps Codex's full context, so point at what's wrong ("you missed X", "this breaks Y") rather than starting a fresh cold job. - Repeat 2–3 until the diff is right, then summarise for the user what changed and what you verified.
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.
- 4d ago First seen · 25 lines · 19 tokens per session scan A 1a9fa5e84e08
codex-review is a command published in the GitHub repository jgt87/codex-offload-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 384 once invoked, about $0.0001 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 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.