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.
git clone --depth 1 https://github.com/Kenmege/codex-claude-companionWrote 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/kenmege/codex-claude-companion/delegate)<a href="https://agentmods.dev/commands/kenmege/codex-claude-companion/delegate"><img src="https://agentmods.dev/badge/commands/kenmege/codex-claude-companion/delegate/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/kenmege/codex-claude-companion/delegate"><img src="https://agentmods.dev/badge/commands/kenmege/codex-claude-companion/delegate.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 | $0.00021 | $0.00328 |
| Opus 5.5 | $0.00008 | $0.00131 |
| Sonnet 5.5 | $0.00004 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
delegate 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 1mo 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
/claude-review:delegate
Preflight
- Resolve the target workspace and preserve existing user changes.
- Choose a repository-native verification command and encode it as a JSON argv
array, for example
["npm","test"]. - Use the current Codex thread ID from
CODEX_THREAD_ID, or pass it explicitly with--thread-id.
Dispatch
Pass the user's request after --:
codex-claude delegate --verify-command '["npm","test"]' -- "<task>"
Use --profile standard unless the user explicitly authorizes another profile.
trusted-autonomous bypasses Claude permission prompts on a cooperative same-UID
host and is not an OS sandbox. sandbox-autonomous is unavailable.
Supervision
Record the returned ccb_... job ID. Use wait, status, logs, send, and
recover against that ID. Treat worker completion, delivery, acknowledgement,
and verification as separate states; do not declare success from process exit
alone.
Result
Return the durable receipt, verification outcome, changed files, and remaining
risks. If delivery or verification failed, report that state explicitly.
With --wait, exit 0 requires completed, independently verified,
origin-acknowledged work; exit 3 reports terminal non-success or a failed
verification/delivery gate; exit 4 reports a pending Claude question.
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.
- 1mo ago First seen · 39 lines · 21 tokens per session scan A 1ac9d76f2485
delegate is a command published in the GitHub repository Kenmege/codex-claude-companion (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 21 tokens to every session and 328 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
pi-code-review
Adversarial code review via Codex — break confidence in changes, not validate them.
pi-fact-check
Fact-check content via Gemini search + Claude verification — cross-provider claim validation.
pi-askall
Ask both Codex and Gemini the same question — get three perspectives with Claude synthesis.
pi-ask-gemini
Ask Gemini a question — get Google's perspective alongside Claude's.
conventions-check
Check AGENTS.md, CLAUDE.md, and the projected agent artifacts (skills, subagents, commands) against the repo's conventions.
register-plugin-asset
A project command for adding a distributable command, agent, or agent skill to a plugin manifest, the file that lists what a plugin provides.