Council v2

A hardened OpenClaw skill for multi-model council reviews.
It dispatches independent reviewers, collects structured JSON, and applies a
mechanical synthesis protocol so the final verdict is driven by votes and
critical findings — not orchestrator vibes.

Primary entrypoint: INLINECODE0

When to Use

Use when a single model reviewing its own work is not enough:

• - Code review before merge or deployment
• Plan review before committing resources
• Architecture review for important technical decisions
• Decision review when multiple plausible options exist
• Security-sensitive or irreversible choices
• Pre-flight review, adversarial critique, or second-opinion work

When Not to Use

Do not use for:

• - One-line fixes or trivial edits
• Low-stakes decisions where overhead exceeds risk
• Purely factual lookups with no judgment call
• Work already reviewed recently with no material change

Council Shape

Two tiers are supported:

• - Standard — 3 reviewers for routine code, plan, and decision reviews
• Full — 5 reviewers for high-stakes, security-sensitive, or irreversible choices

Tier selection heuristic

Use Standard when: routine code changes, internal plans, reversible decisions,
low blast radius. Use Full when: security-critical, production-facing architecture,
irreversible commitments, high cost of being wrong, or when you want maximum coverage.

When in doubt, start Standard. Escalate to Full if the Standard result is split or
if critical findings surface that need more perspectives.

Cost note

Full Council runs 5 model calls instead of 3. That is ~1.7x the token cost of Standard.
Use Full when the cost of a bad decision exceeds the cost of the extra API calls —
which for security, architecture, and irreversible choices, it almost always does.

Detailed role composition and synthesis rules live in:

• - INLINECODE1
• INLINECODE2
• INLINECODE3

Review Types

Definitions: INLINECODE8

Quick Start

CODEBLOCK0

How It Works

1. 1. Loads content from file or stdin
2. Selects Standard or Full tier
3. Builds reviewer prompts from INLINECODE9
4. Emits an orchestration plan suitable for INLINECODE10
5. Collects reviewer JSON outputs
6. Runs INLINECODE11
7. Returns synthesis with mechanical result, minority report, and conditions

Interpreting Results

The synthesizer returns structured JSON and a meaningful exit code:

Reading the synthesis output

• - mechanicalresult: The vote-driven verdict. This is the answer.
• criticalblocks: Any critical findings that auto-blocked approval. Address these first.
• conditions: Aggregated recommendations from warning-level findings. These are your fix list.
• minorityreport: The strongest dissent from the majority. Read this even if you agree with the majority — it is often where the best insight lives.
• anticonsensus_check: Fires on unanimous decisions. Treat the counterargument seriously.

Error Handling

Reviewer returns invalid JSON

INLINECODE16 validates every reviewer output against required fields. If a reviewer
returns malformed JSON, synthesis exits with code 3 and prints an error message.

What to do:

1. 1. Check the raw reviewer output for the failing model
2. Re-run that single reviewer (the orchestration plan shows which models to dispatch)
3. If the model consistently fails, substitute it — see model override flags below

Provider is down or times out

If a provider fails to respond, the review set will be incomplete. Run synthesis on
whatever outputs you have — a 2-of-3 Standard review is still useful. Note the missing
reviewer in your assessment.

Model override flags

Override any model at the command line:
CODEBLOCK1

Available flags: --opus, --gpt, --grok, --deepseek, INLINECODE21

Model Diversity

The council's value comes from different providers with different training data and
different biases reviewing the same decision. The specific model versions (Opus,
GPT-5.4, Grok 4, etc.) matter less than the diversity. Swap in whatever top-tier
models you have access to — what matters is that they are not all from the same
provider.

Retrospectives

INLINECODE22 generates a structured retrospective template for reviewing past
council decisions against actual outcomes.

CODEBLOCK2

When to run retros

Run monthly, or after any decision where the outcome surprised you. The retro surfaces:

• - Which reviewers provided signal vs. noise
• Whether critical findings were real or false alarms
• Whether synthesis preserved minority views accurately
• Prompt changes to consider for role-prompts.md

Feed retro findings back into references/role-prompts.md to calibrate the council.

Notes

• - Requires bash, python3, and OpenClaw reviewer dispatch capability
• Model aliases can be overridden — see model override flags above
• Synthesis rules are documented in INLINECODE26

References

• - references/review-types.md — review type definitions and tier recommendations
• INLINECODE28 — reviewer role prompts and shared output instructions
• INLINECODE29 — JSON schemas for reviewer output and synthesis output
• INLINECODE30 — mechanical synthesis protocol and edge cases