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 skills add WebisityStudio/claude-codex-mcp-bridge --skill review-with-codexgit clone --depth 1 https://github.com/WebisityStudio/claude-codex-mcp-bridgeWrote 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/skills/webisitystudio/claude-codex-mcp-bridge/review-with-codex)<a href="https://agentmods.dev/skills/webisitystudio/claude-codex-mcp-bridge/review-with-codex"><img src="https://agentmods.dev/badge/skills/webisitystudio/claude-codex-mcp-bridge/review-with-codex/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/skills/webisitystudio/claude-codex-mcp-bridge/review-with-codex"><img src="https://agentmods.dev/badge/skills/webisitystudio/claude-codex-mcp-bridge/review-with-codex.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 | $0.00026 | $0.00216 |
| Opus 5.5 | $0.00010 | $0.00086 |
| Sonnet 5.5 | $0.00005 | $0.00043 |
| Haiku 4.5 | $0.00003 | $0.00022 |
Grade A, and why
review-with-codex 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
Review with Codex
Use the review_with_codex MCP tool.
- Put the user's requested focus in
focus. If none was provided, request a general correctness, security and regression review. The project defaults to this session's project. - Codex runs in a read-only sandbox. If the result warns that the workspace changed during the review, tell the user before relying on it.
- If the status is
running_codex, the review arrives in your mailbox frombridge, or callbridge_orchestration_waitwith the run ID. - Verify each reported finding against the local files before presenting it as fact.
- Present findings by severity with file and line references. Say directly when there are no substantive findings.
- Ask for separate approval before making changes, committing or pushing.
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 Changed cab6a536c618
- 2mo ago First seen · 18 lines · 26 tokens per session scan A de608b7ef4b2
review-with-codex is a skill published in the GitHub repository WebisityStudio/claude-codex-mcp-bridge (4 stars, last pushed 6d ago), licensed MIT. It adds 26 tokens to every session and 216 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.
review-with-codex compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| review-with-codexWebisityStudio/claude-codex-mcp-bridge | Skill | 4 | 6d ago | MIT | A | 26 | Claude Code |
| fabric-specmonotykamary/pi-fabric | Skill | 278 | 1mo ago | MIT | A | 50 | Claude Code |
| fabric-advisormonotykamary/pi-fabric | Skill | 278 | 1mo ago | MIT | A | 36 | Claude Code |
| review-teams977043/river-review | Skill | 8 | today | MIT | A | 147 | Claude Code |
| incident-reviewspyrae/kronos-agent-os | Skill | 67 | 25d ago | MIT | A | 21 | Claude Code, Codex |
| loop-convergelevi-qiao/longgraph-skill | Skill | 79 | 1mo ago | MIT | A | 46 | Claude Code |
| eval-code-qualityIbrahim-3d/orchestrator-supaconductor | Skill | 384 | 1mo ago | AGPL-3.0 | A | 109 | Claude Code |