You're offline — showing cached data

Wiki

11-agent-relationships/council-reviews
2026-06-13 07:28:52 SAST
Wiki Home → 11-agent-relationships/council-reviews

Council Reviews

Council reviews are a multi-model quality gate where external AI models review work done by Claude Code agents. They are implemented via the second-opinion skill and are a standard part of the workflow -- not a last resort.

Two Modes

Mode A: Single Model (Debugging)

When debugging has failed after 2-3 attempts, get a fresh perspective from one model. Codex is the default because it can read actual repo files via CLI.

Mode B: Full Council (Architecture Review)

For architecture reviews, post-implementation audits, or design validation, run all models in parallel and compile a combined view.

Available Models

Backend Method Speed Cost Strengths
Codex CLI (codex exec, read-only) ~120-140s Free (ChatGPT sub) Strategic gaps, control-plane issues; reads actual repo files
Gemini REST API (GEMINI_API_KEY) ~1-5s Free (AI Studio) Operational risks, security, env/config, deployment concerns
Kimi REST API (KIMI_CODE_API_KEY) ~3-10s Free (Kimi Coding sub) Detailed code-level review, finds inconsistencies
Kimi-CLI CLI subprocess ~100-200s Free Same as Kimi but reads local files (use only when needed)
Minimax REST API (MINIMAX_API_KEY) ~3-5s Free (MiniMax sub) Independent perspective, different training data, catches groupthink
Opus Subagent (model: opus) ~55s Claude usage Nuanced assessment, race conditions, subtle bugs

All backends are free (existing subscriptions or free-tier API keys). No paid API calls.

When Council Reviews Auto-Trigger

These triggers are mandatory -- agents invoke them without waiting to be asked:

Trigger Minimum Models Timing
Dev loop completes, 3+ files changed Gemini + Codex After reviewer approves, before marking done
Infrastructure changes (systemd, cron, scheduler, SSH) Gemini + Codex Before marking done
Architecture decision (new node, service, integration) All models Before committing direction
Security-touching changes (auth, tokens, keys, permissions) Gemini + Codex Non-negotiable
Larry ticket review finds CRITICAL/IMPORTANT Gemini Before resetting ticket to todo
Monthly architecture review All models With Solutions Architect

Rule: If about to mark a significant task "done" and council has not run -- run it first. Takes 30-120 seconds.

How It Works

Single Model Flow

  1. Package context: problem description, error output, relevant code (~200 lines max), what was tried, specific question
  2. Call: python ~/.claude/skills/second-opinion/scripts/ask_second_opinion.py -b codex "PROMPT"
  3. Present: quote the diagnosis, state agreement/disagreement, propose combined fix

Full Council Flow

  1. Write context to a .txt prompt file (architecture summary + implementation + questions)
  2. Launch all 5 backends in parallel as background tasks
  3. Compile results as they land (don't wait for all -- present partial results)
  4. Build combined view: what all models agree on (high confidence), unique findings per model, own assessment
  5. Clean up prompt and output files

Override Rules

11-agent-relationships/lucienne|Lucienne can overrule council findings when:

Overrides must always include an explanation of why.

Larry-Specific Review

When 11-agent-relationships/larry|Larry completes a ticket:

  1. review_larry_work() runs a code reviewer on the git diff
  2. If reviewer finds CRITICAL or IMPORTANT issues, Gemini validates before resetting to todo
  3. This prevents false positives from the reviewer causing unnecessary rework

Platform Support

Platform Codex Gemini Kimi
Windows CLI via bash (use -f for long prompts) API CLI via cmd.exe bat script
Linux (Luci) CLI directly API CLI directly
macOS CLI directly API CLI directly

Key Files

Key Takeaways

Help