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/enable)<a href="https://agentmods.dev/commands/kenmege/codex-claude-companion/enable"><img src="https://agentmods.dev/badge/commands/kenmege/codex-claude-companion/enable/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/enable"><img src="https://agentmods.dev/badge/commands/kenmege/codex-claude-companion/enable.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 | $0.00014 | $0.00529 |
| Opus 5.5 | $0.00006 | $0.00212 |
| Sonnet 5.5 | $0.00003 | $0.00106 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade B, and why
enable scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `--config <path>` — override Codex config path and force the legacy TOML registration path (default: `$CODEX_HOME/config.toml` or `~/.codex/config.toml`) How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/claude-review:enable
Register the claude-review plugin in Codex. On current Codex CLI versions, the helper uses the native codex plugin marketplace add and codex plugin add path through a local wrapper marketplace under $CODEX_HOME/~/.codex. On older Codex runtimes or explicit --config overrides, it falls back to writing the legacy [marketplaces.claude-review-private] source entry and [plugins."claude-review@claude-review-private"] enable stanza.
Safe to re-run: native installs are refreshed idempotently, and legacy config writes preserve existing content while repairing stale source = paths, normalising source_type to "local", and flipping enabled = false back to true.
Preflight
- Plugin installed via
npm install -g codex-claude-companionafter npmjs publish, ornpm install -g .from a cloned checkout. - Codex CLI installed and
~/.codex/directory exists (created automatically if absent).
Commands
# Register the plugin (run once after install)
codex-claude enable
# Preview what would be written without touching the config
codex-claude enable --dry-run
# Machine-parseable output
codex-claude enable --json
# Override config path (useful in CI or non-standard installs)
codex-claude enable --config /path/to/config.toml
Flags
--json— emit machine-parseable registration status--dry-run— show what would be installed or appended without modifying Codex config--config <path>— override Codex config path and force the legacy TOML registration path (default:$CODEX_HOME/config.tomlor~/.codex/config.toml)
After Running
Restart Codex CLI to load the plugin. Slash commands then available:
/claude-review:delegate, /claude-review:wait, /claude-review:logs,
/claude-review:send, /claude-review:recover,
/claude-review:bridge-doctor, /claude-review:workspace,
/claude-review:review, /claude-review:elite-review,
/claude-review:deep-review, /claude-review:security-review, and
/claude-review:setup.
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 · 47 lines · 14 tokens per session scan B cfb74645952c
enable is a command published in the GitHub repository Kenmege/codex-claude-companion (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 14 tokens to every session and 529 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.