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/tornikegomareli/claude-plugin-codex/setupgit clone --depth 1 https://github.com/tornikegomareli/claude-plugin-codexWhat 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 | $0.00049 | $0.00649 |
| Opus 5 | $0.00024 | $0.00324 |
| Sonnet 5 | $0.00010 | $0.00130 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
setup 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.
What it actually says
Check whether Claude Code is ready for delegation, and manage the optional stop-time review gate.
Raw slash-command arguments:
$ARGUMENTS
Locating the companion script:
- The companion script is
scripts/claude-companion.mjsinside this plugin's root directory (the installedclaudeplugin directory that contains.codex-plugin/plugin.json). - Always invoke it with an absolute path.
Flow:
- Run:
node "<plugin-root>/scripts/claude-companion.mjs" setup --json $ARGUMENTS
- If the report shows Claude Code is not installed and npm is available, ask the user exactly once, in plain conversation, with "Install Claude Code (Recommended)" first and "Skip for now" second. If they accept, run
npm install -g @anthropic-ai/claude-code, then rerun the setup command. - If Claude Code is installed but not authenticated, tell the user to run
claudeinteractively and use/loginto sign in. Mentionclaude setup-tokenfor headless machines. - If the report shows
ready: trueanddefaultModelis null and the user did not pass--modelor--clear-model: ask the user exactly once, in plain conversation, which model Claude should use for delegated tasks in this repository, with these options — "Claude Code's own default (Recommended)", "sonnet", "opus", "haiku". If they pick a specific model, run the setup command again with--model <choice>. If they keep the default, change nothing. - Rerun the setup command without
--jsonand present the rendered report verbatim.
Default model:
--model <model>stores a default Claude model for this repository (haiku,sonnet,opus,fable, or a full model name;fastmaps tohaiku). All delegated runs use it unless a per-run--modeloverrides it.--clear-modelremoves the stored default so Claude Code's own default model applies again.
Review gate:
--enable-review-gateturns on a Stop hook that runs a Claude review of each Codex turn before the session can end, and blocks if it finds issues. Warn the user that this can create long Claude/Codex loops and consume usage quickly.--disable-review-gateturns it off.
Sandbox requirements:
- The companion spawns the
claudeCLI, which needs network access to reach the Anthropic API. - If the sandbox blocks the command or Claude reports a connection error, rerun the same shell command with escalated permissions and explain why in the justification.
- Do not work around a sandbox denial by improvising your own review or edits; the command's value is Claude's independent output.
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 · 36 lines · 49 tokens per session scan A 51a0394a6b0e
setup is a command published in the GitHub repository tornikegomareli/claude-plugin-codex (9 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 649 once invoked, about $0.0002 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.
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.