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 wangsiyi7/grok-codex-bridge --skill grok-second-opiniongit clone --depth 1 https://github.com/wangsiyi7/grok-codex-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/wangsiyi7/grok-codex-bridge/grok-second-opinion)<a href="https://agentmods.dev/skills/wangsiyi7/grok-codex-bridge/grok-second-opinion"><img src="https://agentmods.dev/badge/skills/wangsiyi7/grok-codex-bridge/grok-second-opinion/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/wangsiyi7/grok-codex-bridge/grok-second-opinion"><img src="https://agentmods.dev/badge/skills/wangsiyi7/grok-codex-bridge/grok-second-opinion.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 | $0.00061 | $0.00335 |
| Opus 5 | $0.00030 | $0.00168 |
| Sonnet 5 | $0.00012 | $0.00067 |
| Haiku 4.5 | $0.00006 | $0.00034 |
Grade A, and why
grok-second-opinion 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 9d 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
Grok second opinion
Use the grok-bridge MCP tools as a read-only advisory lane. The bridge reuses the user's local Grok Build login and never asks for an API key.
Routing
- Use
ask_grokfor a focused question with optional pasted context. - Use
plan_with_grokfor an independent implementation or decision plan. - Use
review_with_grokonly with a diff, snippet, or document the user has already placed in scope. - Use
compare_with_grokafter Codex has a draft answer and synthesis would improve confidence.
Boundaries
- Tell the user when Grok is being consulted.
- Do not send passwords, tokens, private keys,
.envcontents, or unrelated private files. - Keep context minimal and task-relevant; prefer diffs over whole repositories.
- Treat Grok output as advisory evidence, not authority. Reconcile disagreements explicitly.
- The bridge intentionally disables Grok memory, planning, subagents, and automatic updates for each advisory call.
- If the bridge reports that Grok is missing or signed out, run the repository doctor or ask the user to complete
grok login.
Response shape
Return the synthesized answer first. When useful, add one short sentence explaining what Grok changed or confirmed.
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.
- 9d ago First seen · 29 lines · 61 tokens per session scan A 29a203d54ee0
grok-second-opinion is a skill published in the GitHub repository wangsiyi7/grok-codex-bridge (0 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 335 once invoked, about $0.0003 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.