second-opinion
Use when you want an independent second opinion from a different AI model (OpenAI Codex CLI).
Skill by cmillstead
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/cmillstead-second-opinion
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/second-opinion
What's inside
- Skill name
second-opinion- Description
- Use when you want an independent second opinion from a different AI model (OpenAI Codex CLI). Three modes: review (pass/fail gate on a plan or diff), challenge (adversarial — actively tries to break your code), and consult (open-ended question to a different model). Use after /review for cross-model coverage, or during Phase 4 planning for independent plan validation. Requires Codex CLI installed: npm install -g @openai/codex
- License
- unknown
- Instructions
- 197 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (46)
- SKILL.md
- codex-learnings-digest.md
- codex-learnings-review-digest.md
- 20260624-062659-64a5-test-fixture-no-route-vacuous.md · codex-learnings.d/
- 20260624-062659-dac1-cfgtest-as-production-path.md · codex-learnings.d/
- 20260624-193512-0b37-rowcount-write-nonunique-key.md · codex-learnings.d/
- 20260626-201509-c406-typed-key-cast-throws-before-fallback.md · codex-learnings.d/
- 20260701-133000-0f84-dedup-jobid-retained-on-failure.md · codex-learnings.d/
- 20260701-133000-a35d-role-migration-revoke-stale-grants.md · codex-learnings.d/
- 20260702-060939-19b2-early-return-shadows-required-gate.md · codex-learnings.d/
- 20260702-184931-0bb9-whole-object-pin-missing-keyset.md · codex-learnings.d/
- 20260723-170559-5689-self-heal-migration-schema-shape.md · codex-learnings.d/
- 20260725-034000-9f2c-dual-resolution-policy-one-input.md · codex-learnings.d/
- 20260729-051257-b016-vacuous-assertion.md · codex-learnings.d/
- 20260805-035925-fa2a-correction-introduces-unverified-claims.md · codex-learnings.d/
- 20260806-023926-0636-literal-scan-misses-var-pairs.md · codex-learnings.d/
- 20260823-211710-22a7-user-args-override-daemon-args.md · codex-learnings.d/
- README.md · codex-learnings.d/_graduated/
- c01-single-gate-path-trust.md · codex-learnings.d/_graduated/
- _header.md · codex-learnings.d/
- c02-sentinel-semantics-reject.md · codex-learnings.d/
- c03-ci-venv-missing.md · codex-learnings.d/
- c04-lossy-stash-invariant.md · codex-learnings.d/
- c05-test-hermeticity.md · codex-learnings.d/
- c10-command-grammar-completeness.md · codex-learnings.d/
- c11-select-threading-alternative-score.md · codex-learnings.d/
- c12-concurrency-lock-ttl.md · codex-learnings.d/
- c13-default-flip-side-branches.md · codex-learnings.d/
- c14-allowlist-flag-hardening.md · codex-learnings.d/
- c15-migration-parity-schema.md · codex-learnings.d/
- c16-tenant-isolation-fk-scope.md · codex-learnings.d/
- c17-path-equality-segment-aligned.md · codex-learnings.d/
- c18-metric-granularity-mismatch.md · codex-learnings.d/
- c19-dead-arm-dispatch.md · codex-learnings.d/
- p01-phantom-symbol.md · codex-learnings.d/
- p02-wrong-api-shape.md · codex-learnings.d/
- p03-stale-command.md · codex-learnings.d/
- p04-wrong-identifier.md · codex-learnings.d/
- p30-helper-reuse-body.md · codex-learnings.d/
- p31-none-sentinel-aggregate.md · codex-learnings.d/
- p32-negative-existence-claim.md · codex-learnings.d/
- p33-ambiguity-over-deny.md · codex-learnings.d/
- codex-learnings.md
- reference.md
- build-digest.py · scripts/
- test_build_digest.py · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from cmillstead/coding-team
- 0.524score
coding-team
cmillstead
Use when starting any code task — new features, refactors, significant bug fixes, or any work that benefits from specialist design review.
SkillBFreshness: BClaude Code +9 - 0.519score
a11y
cmillstead
WCAG 2.2 AA source code audit — reviews HTML/templates for semantic markup, ARIA usage, keyboard navigation, contrast, and focus management.
SkillBFreshness: BClaude Code +9 - 0.519score
api-qa
cmillstead
Use when testing API endpoints for contract compliance, error handling, security, and performance.
SkillBFreshness: BClaude Code +9 - 0.519score
debug
cmillstead
Use when investigating a bug, test failure, or unexpected behavior.
SkillBFreshness: BClaude Code +9 - 0.519score
doc-write
cmillstead
Use when writing documentation from scratch or improving existing docs.
SkillBFreshness: BClaude Code +9 - 0.519score
incident
cmillstead
Use when coordinating a production incident, building incident response processes, or running post-mortems.
SkillBFreshness: BClaude Code +9 - 0.519score
harness-engineer
cmillstead
Use when designing or auditing Claude Code harness infrastructure — hooks, rules, settings, constraint gaps, maturity assessment, and verifying whether past…
SkillBFreshness: BClaude Code +9 - 0.519score
prompt-craft
cmillstead
Write or audit Claude Code SKILL.md files, CLAUDE.md instructions, and agent prompt templates — CC-specific patterns like named rationalizations, identity…
SkillBFreshness: BClaude Code +9 - 0.519score
dep-audit
cmillstead
Use when auditing project dependencies for staleness, license risks, upgrade paths, and health.
SkillBFreshness: BClaude Code +9 - 0.516score
doc-sync
cmillstead
Use after shipping a feature to update project documentation.
SkillBFreshness: BClaude Code +9 - 0.516score
release
cmillstead
Push and create PR from within the coding-team pipeline — syncs branch, runs tests, reviews diff, pushes, creates PR, and optionally merges.
SkillBFreshness: BClaude Code +9 - 0.494score
tdd
cmillstead
Use when implementing any feature or fix using test-driven development.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Sep 2, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/cmillstead/coding-team
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from cmillstead
- 0.524score
coding-team
cmillstead
Use when starting any code task — new features, refactors, significant bug fixes, or any work that benefits from specialist design review.
SkillBFreshness: BClaude Code +9 - 0.519score
api-qa
cmillstead
Use when testing API endpoints for contract compliance, error handling, security, and performance.
SkillBFreshness: BClaude Code +9 - 0.519score
a11y
cmillstead
WCAG 2.2 AA source code audit — reviews HTML/templates for semantic markup, ARIA usage, keyboard navigation, contrast, and focus management.
SkillBFreshness: BClaude Code +9 - 0.519score
debug
cmillstead
Use when investigating a bug, test failure, or unexpected behavior.
SkillBFreshness: BClaude Code +9 - 0.519score
doc-write
cmillstead
Use when writing documentation from scratch or improving existing docs.
SkillBFreshness: BClaude Code +9 - 0.519score
incident
cmillstead
Use when coordinating a production incident, building incident response processes, or running post-mortems.
SkillBFreshness: BClaude Code +9
Cite this page
second-opinion skill. Agent Mart. https://agentmart.dev/skills/cmillstead-second-opinion (last updated 2026-10-24)