gaze: Command for Claude Code

.opencode/commands/uf.review-council.md

uf.review-council is a command for Claude Code, OpenCode from unbound-force/gaze. It costs 13 tokens per session (9,241 once invoked), scanned A, original, Apache-2.0.

A command that runs a structured review of a codebase or specification against its rules. It gathers findings, checks review status, and asks for confirmation before posting a review.

In plain words
What is it for?
Use it to audit code changes, compare them with a specification, consolidate review findings, and guide fixes through several review rounds.
Why use it?
It reduces the chance that important compliance issues are missed or that review comments are posted without human approval.

Command for Claude CodeOpenCode

Written for Claude Code and OpenCode: $ARGUMENTS substitution, but also installed under .opencode/. Also seen: mentions AGENTS.md; mentions OpenCode.

This is unbound-force/gaze's own configuration. It tells Claude Code and OpenCode how to work on gaze itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gaze configures →

Reuse

Borrowing it

Nothing to install: this file belongs to unbound-force/gaze. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/unbound-force/gaze/main/.opencode/commands/uf.review-council.md
Clone the repo
git clone --depth 1 https://github.com/unbound-force/gaze

Made for: Claude Code, OpenCode.

Wrote 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.

agentmods badge for uf.review-council

README.md
[![agentmods](https://agentmods.dev/badge/commands/unbound-force/gaze/uf.review-council/github.svg)](https://agentmods.dev/commands/unbound-force/gaze/uf.review-council)
Your own site
<a href="https://agentmods.dev/commands/unbound-force/gaze/uf.review-council"><img src="https://agentmods.dev/badge/commands/unbound-force/gaze/uf.review-council/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.

agentmods 80×15 button for uf.review-council

Your own site · 80×15
<a href="https://agentmods.dev/commands/unbound-force/gaze/uf.review-council"><img src="https://agentmods.dev/badge/commands/unbound-force/gaze/uf.review-council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,241 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00013 $0.09241
Opus 5 $0.00006 $0.04620
Sonnet 5 $0.00003 $0.01848
Haiku 4.5 $0.00001 $0.00924

Measured 7d ago against content hash f3c7bfa4f536, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

uf.review-council 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 7d 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.

.opencode/commands/uf.review-council.md · 936 lines

How it starts

The opening of the file, as written. The whole thing — 936 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command: /uf.review-council

Session-resume guard: If this session was resumed from compressed context, re-read this entire template before continuing. Do NOT infer step completion from compressed summaries. Check the EXECUTION CHECKLIST below for actual completion state. If the checklist shows unchecked items, resume from the first unchecked item. When in doubt, re-read — false re-reads are harmless; skipping steps due to stale context causes incomplete reviews or unauthorized actions.

EXECUTION CHECKLIST — Update each item using the Edit tool as you complete it. Mark [x] when done.

  • Phase 1a: Pre-flight checks
  • Phase 1b: Gaze quality analysis
  • Phase 1c: Review context discovery
  • Step 2: Divisor agent delegation (full branch diff)
  • Step 3: Finding consolidation
  • Step 4: Fix loop (iteration: _/3)
  • Step 5: Iteration limit check
  • Step 6: Final report
  • Step 7a: PR detection
  • Step 7b: Review state fetching
  • Step 7c: Pre-posting checks
  • Step 7d: Finding aggregation
  • Step 7e: Inline comment preparation
  • Step 7f: Human confirmation (MANDATORY GATE)
  • Step 7g: Post review

User Input

$ARGUMENTS

Description

Review the current codebase or SpecKit artifacts for compliance with the Behavioral Constraints in AGENTS.md using the review council. The council dynamically discovers which reviewer agents are available rather than assuming a fixed set.

Determine Review Mode

The review mode is determined automatically by examining the workspace state. The user can also force a mode explicitly.

Explicit Override

If $ARGUMENTS contains the word "specs", use Spec Review Mode regardless of auto-detection.

If $ARGUMENTS contains the word "code", use Code Review Mode regardless of auto-detection.

PR Number Argument

After removing mode keywords ("specs", "code") from $ARGUMENTS, check if the remaining text contains a positive integer. If so, validate it:

Read the full file on GitHub · 936 lines

Changes

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.

  1. 7d ago Changed · +60 lines f3c7bfa4f536
  2. 10d ago First seen · 876 lines · 13 tokens per session scan A 7c2e3a1b081d

Subscribe to this mod's changes

uf.review-council is a command published in the GitHub repository unbound-force/gaze (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 13 tokens to every session and 9,241 once invoked, about $0.0001 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.