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 nikolamin/claude-coordinator-kit --skill codex-second-opiniongit clone --depth 1 https://github.com/nikolamin/claude-coordinator-kitWrote 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/nikolamin/claude-coordinator-kit/codex-second-opinion)<a href="https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/codex-second-opinion"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/codex-second-opinion.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 | $0.00141 | $0.00920 |
| Opus 5 | $0.00071 | $0.00460 |
| Sonnet 5 | $0.00028 | $0.00184 |
| Haiku 4.5 | $0.00014 | $0.00092 |
Grade A, and why
codex-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 3d 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.
Codex / GPT second-opinion — setup
Optional. Gives the coordinator's dispatched agents a second, differently-trained model opinion
(GPT, via OpenAI's Codex CLI) on judgment-heavy work: UI/UX design decisions, copy/copywriting,
research tasks, and reviewing generated documents. Why bother: a coordinator that only
self-reviews with the same model family has a blind-spot problem — a second model catches
different failure modes. See CLAUDE.md's Escalation section for when it fires; this file covers
install and invocation.
Install
npm install -g @openai/codex
Requires Node. Same PATH gotcha as the Telegram bridge: launchd/systemd-spawned processes get a
minimal PATH that excludes nvm/homebrew-managed bin dirs, so a bare codex (like a bare
claude) resolves in your interactive shell but not in a service-spawned one. On Windows, a Task
Scheduler task has the same problem — it doesn't see PATH additions made by a shell profile — so
use the absolute path to the codex binary there too (typically %APPDATA%\npm\codex.cmd). See
telegram-bridge/SETUP.md's PATH note if anything other than an interactive session or a
dispatched agent will invoke it.
Login
codex login is an interactive OAuth flow, normally run by whoever owns the OpenAI account it
authenticates. Before first use, an agent checks auth state with:
codex login status
If not logged in, that's a graceful-degradation case (below), not something to work around.
Headless invocation
codex exec is the claude -p equivalent — one-shot, non-interactive:
codex exec "<prompt>"
Key flags:
-o, --output-last-message <file>— write only the final reply to a file under.coordinator-scratch/(skip the run log).-s, --sandbox <read-only|workspace-write>— sandbox level;read-onlyfor review/opinion work,workspace-writeonly if it genuinely needs to edit files.--skip-git-repo-check— required when running outside a git repo.-C <dir>— run with a different working directory.--json— machine-readable event output.
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.
- 3d ago Changed · +2 lines 1d29d112642f
- 7d ago First seen · 80 lines · 141 tokens per session scan A 400abf71b1f5
codex-second-opinion is a skill published in the GitHub repository nikolamin/claude-coordinator-kit (2 stars, last pushed 5d ago), licensed MIT. It adds 141 tokens to every session and 920 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…