What is cross-family-review?

A review process that sends work to an independent model from a different AI family and returns an accept, partial, or reject verdict with reasons. It applies this review at specified points in the Manager, Collaborator, Admin, and Consultant lifecycle.

Use it for required pre-handoff reviews, high-stakes collaborator handoffs, and later lifecycle checks using the provided fleet dispatch command.

It adds a separate technical perspective and enforces that the reviewer is not from the same AI family as the implementing role. This can expose issues before work is handed to another role or closed.

cross-family-review — Skill for Claude Code by chf3198

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/chf3198/copilot-governance

agentmods

npx agentmods add skills/chf3198/copilot-governance/cross-family-review

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/chf3198/copilot-governance/cross-family-review/github.svg)](https://agentmods.dev/skills/chf3198/copilot-governance/cross-family-review)

Your own site

<a href="https://agentmods.dev/skills/chf3198/copilot-governance/cross-family-review"><img src="https://agentmods.dev/badge/skills/chf3198/copilot-governance/cross-family-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/chf3198/copilot-governance/cross-family-review"><img src="https://agentmods.dev/badge/skills/chf3198/copilot-governance/cross-family-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 893 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00053	$0.00893
Opus 5	$0.00026	$0.00447
Sonnet 5	$0.00011	$0.00179
Haiku 4.5	$0.00005	$0.00089

Measured 12d ago against content hash d0c49577756b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cross-family-review scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

# Direct curl (fallback when dispatcher unavailable)

skills/cross-family-review/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Family Review Skill

Purpose

Dispatches to a non-Anthropic fleet model (Qwen via Ollama) and returns a structured verdict. Implements the cross-family independence contract: the reviewing model's AI family MUST differ from the implementing role's family.

Lifecycle Points

Point	Who	When	Required?
L1	Manager	Pre-implementation orientation	Advisory
L2	Collaborator	Pre-COLLABORATOR_HANDOFF	REQUIRED
L3	Admin	Receipt of COLLABORATOR_HANDOFF	REQUIRED
L4	Consultant	Pre-CONSULTANT_CLOSEOUT	REQUIRED
L5	Manager	Tier-2 anneal on repeated same-family	Advisory

Use L2 before every COLLABORATOR_HANDOFF. L3 and L4 are CI-gated.

Invocation

# L2 — standard (7B fast, ~30-60s)
node scripts/global/fleet-red-team-dispatch.js \
  --artifact-type collaborator-handoff \
  --ticket <N> \
  --model qwen2.5-coder:7b

# L2 — high-stakes (32B, ~3-5 min)
node scripts/global/fleet-red-team-dispatch.js \
  --artifact-type collaborator-handoff \
  --ticket <N> \
  --model qwen2.5-coder:32b

# Direct curl (fallback when dispatcher unavailable)
curl -s -X POST http://100.91.113.16:11434/api/generate \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen2.5-coder:7b","prompt":"<review prompt>","stream":false}'

Model Routing (G3 fleet-first)

Dispatch order: 36gbwinresource (100.91.113.16) → OpenClaw (100.78.22.13) → paid.

If all fleet nodes unavailable: record fleet_unavailable: true in handoff. Do NOT substitute a same-family model. Defer if needed (G6 degradation).

Required Output Fields

COLLABORATOR_HANDOFF (L2)

cross_family_reviewer: qwen2.5-coder:[email protected]
cross_family_rating: <N>/100
reviewer_family: qwen
cross_family_findings: <findings>

CONSULTANT_CLOSEOUT (L4)

cross_family_verdict: ACCEPT|PARTIAL|REJECT — <model@host> — <rationale>

Advisory vs. Blocking

L1, L5: advisory only (no CI gate).
L2: advisory in current soak; CI hard-gate after Epic #2511 C3 promotion.
L3: hard-gate via admin-gate in baton-gates.yml (reviewer_family_verified).
L4: advisory in current soak via GATE_ADVISORY_MODE=1; promote to blocking by unsetting GATE_ADVISORY_MODE in baton-gates.yml consultant-gate job.

Read the full file on GitHub · 89 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.

12d ago First seen · 89 lines · 53 tokens per session scan A d0c49577756b

Subscribe to this mod's changes

cross-family-review is a skill published in the GitHub repository chf3198/copilot-governance (2 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 893 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Code review

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

full-repo-review

Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.

notque/vexjoy-agent · 22 tokens

agent-teams-simplify-and-harden

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…

LeoYeAI/openclaw-master-skills · 115 tokens

cross-family-review