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/workspace)<a href="https://agentmods.dev/commands/kenmege/codex-claude-companion/workspace"><img src="https://agentmods.dev/badge/commands/kenmege/codex-claude-companion/workspace.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 5.1 | $0.00013 | $0.00781 |
| Opus 5 | $0.00006 | $0.00391 |
| Sonnet 5 | $0.00003 | $0.00156 |
| Haiku 4.5 | $0.00001 | $0.00078 |
Grade A, and why
workspace 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/claude-review:workspace
Compatibility lane: use
/claude-review:delegatefor new durable tmux-owned jobs with recovery, collaboration, delivery acknowledgement, and independent verification.
Purpose
Keep this Codex task active as the planner, orchestrator, verifier, and reviewer.
Dispatch Claude Code as a writable background worker, then open Claude's native
agents control panel in a separate terminal. Claude may edit files, run tools,
and execute tests under its native permission controls. Existing review commands
remain isolated and read-only.
Preflight
- Prefer
codex-claudeon PATH; fall back tocodex-claude-review. - Record the branch,
git status --short, and the repository's real verification commands. Preserve all pre-existing user changes. - Keep the exact user request as the worker prompt. Never add a permission-bypass flag or start another Codex process in this legacy lane.
Dispatch
Use an explicit option terminator before the coding request so request text that starts with a dash can never be reinterpreted as a plugin option:
codex-claude workspace [workspace-flags] -- "<coding request>"
The command returns the authoritative short Claude session ID immediately.
Claude continues under its background supervisor and its agents panel opens
in another terminal. This Codex task must remain responsive; do not attach
Claude to the Codex terminal or wait synchronously for the panel to close.
Claude defaults to the rolling opus selector. The user may pass --model <selector> or change models through Claude's native controls. --plan is
analysis-only; normal mode is full coding with native approvals. The GPT-side
model is inherited automatically because this active Codex task performs the
orchestration—there is no nested GPT model selection.
Supervise
- Poll
codex-claude workspace-status --path <directory> --all --jsonat a reasonable cadence while continuing to communicate progress. - Use
codex-claude workspace-logs <session-id>only when detail is needed. - The user may interact directly in the separate Claude panel. Do not compete with user input or overwrite user-owned work.
- If a focused repair is needed, dispatch it with
codex-claude workspace --path <directory> --no-panel -- "<repair request>"to avoid duplicate panels. - Use
codex-claude workspace-stop <session-id>only when the user asks, the task is obsolete, or continuing would be unsafe.
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.
- 8d ago First seen · 82 lines · 13 tokens per session scan A 2ea0597153e9
workspace is a command published in the GitHub repository Kenmege/codex-claude-companion (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 13 tokens to every session and 781 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
lint
Check the project for naming, security and best-practice issues.
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.