deliberated-review

deliberated-review is a skill for Claude Code, Codex from justinstimatze/gemot. It costs 32 tokens per session (1,379 once invoked), scanned A, original, Apache-2.0.

A code-review workflow that asks several specialist reviewers to examine the same code, then investigates why their opinions differ.

In plain words
What is it for?
Use it for pull-request reviews and architecture choices where reviewers may recommend conflicting changes. It requires the gemot review service to be configured.
Why use it?
It reduces the risk of relying on one reviewer’s blind spots and helps resolve disagreements about security, reliability, performance, or design.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it for pull-request reviews and architecture choices where reviewers may recommend conflicting changes. It requires the gemot review service to be configured.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/justinstimatze/gemot/deliberated-review
Install

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.

Any agent
npx skills add justinstimatze/gemot --skill deliberated-review
Clone the repo
git clone --depth 1 https://github.com/justinstimatze/gemot

Made for: Claude Code, Codex.

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 deliberated-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/justinstimatze/gemot/deliberated-review/github.svg)](https://agentmods.dev/skills/justinstimatze/gemot/deliberated-review)
Your own site
<a href="https://agentmods.dev/skills/justinstimatze/gemot/deliberated-review"><img src="https://agentmods.dev/badge/skills/justinstimatze/gemot/deliberated-review/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 deliberated-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/justinstimatze/gemot/deliberated-review"><img src="https://agentmods.dev/badge/skills/justinstimatze/gemot/deliberated-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,379 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 $0.00032 $0.01379
Opus 5 $0.00016 $0.00690
Sonnet 5 $0.00006 $0.00276
Haiku 4.5 $0.00003 $0.00138

Measured 10d ago against content hash c787503d7fc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

deliberated-review 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 10d 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.

integrations/hermes-agent/skills/deliberated-review/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deliberated Code Review

When you need a thorough code review from multiple perspectives, delegate to specialist reviewers, cross-vote, and use gemot to find the crux of any disagreements.

When to Use

  • PR review where security, performance, and correctness might conflict
  • Architecture decisions where subagents return different recommendations
  • Any multi-perspective review where you need to know WHY reviewers disagree, not just THAT they disagree

Process

Step 1: Delegate specialist reviews

Use delegate_task to spawn 3 independent reviewers. Each reviews the same code from their expertise:

delegate_task([
  {"goal": "Review this code for security vulnerabilities. Cite specific lines, explain attack vectors, suggest fixes.", "context": "<the code>"},
  {"goal": "Review this code for reliability and correctness. Cite specific lines, explain what breaks, suggest fixes.", "context": "<the code>"},
  {"goal": "Review this code for performance issues. Cite specific lines, estimate impact, suggest fixes.", "context": "<the code>"}
])

Step 2: Create a gemot deliberation

Call mcp_gemot_deliberation with:

  • action: "create"
  • topic: a one-line summary of what's being reviewed (e.g., "Payment processing code review")
  • template: "review"
  • group_id: a consistent identifier for the project or workflow (e.g., "myproject-reviews")

Step 3: Submit each reviewer's findings

For each subagent result, call mcp_gemot_participate with:

  • action: "submit_position"
  • deliberation_id: from step 2
  • agent_id: the reviewer role (e.g., "security-reviewer")
  • content: the reviewer's full findings

Step 4: Cross-vote

Call mcp_gemot_participate with action: "get_positions" to fetch all positions. Then have each reviewer vote on the other reviewers' findings:

For each position, each OTHER reviewer calls mcp_gemot_participate with:

  • action: "vote"
  • deliberation_id: from step 2
  • agent_id: the voting reviewer's ID
  • position_id: the position being voted on
  • value: 1 (agree with this finding), 0 (no opinion), or -1 (disagree)

Read the full file on GitHub · 111 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. 10d ago First seen · 111 lines · 32 tokens per session scan A c787503d7fc4

Subscribe to this mod's changes

deliberated-review is a skill published in the GitHub repository justinstimatze/gemot (3 stars, last pushed 5d ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,379 once invoked, about $0.0002 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.