Borrowing it
Nothing to install: this file belongs to jgt87/codex-offload-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jgt87/codex-offload-mcp/main/.claude/commands/codex-draft.mdgit 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-draft)<a href="https://agentmods.dev/commands/jgt87/codex-offload-mcp/codex-draft"><img src="https://agentmods.dev/badge/commands/jgt87/codex-offload-mcp/codex-draft/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/jgt87/codex-offload-mcp/codex-draft"><img src="https://agentmods.dev/badge/commands/jgt87/codex-offload-mcp/codex-draft.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00017 | $0.00240 |
| Opus 5.5 | $0.00007 | $0.00096 |
| Sonnet 5.5 | $0.00003 | $0.00048 |
| Haiku 4.5 | $0.00002 | $0.00024 |
Grade A, and why
codex-draft 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 2mo 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 draft→refine: Codex writes the bulk cheaply, you polish it with context.
Task: $ARGUMENTS
- Draft on Codex with
codex_start(prompt, cwd)— ask for a straightforward first pass, not a finished product. A lowerreasoningEffortis usually right; the goal is bulk output fast, and this keeps the expensive output tokens on Codex's side, not yours. - Collect with
codex_resultand read the changed files. - Refine in-process. Do the judgement-heavy part yourself — the edits that need this conversation's context, taste, or knowledge of the wider codebase. This is the half worth your tokens.
Reach for this when the bulk is cheap to generate but the polish needs context. If the whole thing
needs your judgement, just do it in-process; if none of it does, a plain codex_start is enough.
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.
- 2mo ago First seen · 20 lines · 17 tokens per session scan A 821b97b79992
codex-draft is a command published in the GitHub repository jgt87/codex-offload-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 240 once invoked, about $0.0001 per session on Opus 5.5. 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.