enforcing-review-separation

enforcing-review-separation is a skill for Claude Code from Nolane-x/forge-os. It costs 34 tokens per session (183 once invoked), scanned A, original, MIT.

A procedure for requiring an independent person or group to review an artifact, code change, finding, provider, or release before approval. Independent means the reviewer is separated from the people who produced or resolved the item.

In plain words
What is it for?
Use it to define reviewer boundaries, connect the authorized reviewer to the evidence, and enforce separation across roles, teams, or trust domains.
Why use it?
It reduces the risk that one person or trusted group approves its own work without an independent check.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the forgeos plugin — 196 skills, 1 command, 1 agent, 1 MCP server shipped together

Good fit Use it to define reviewer boundaries, connect the authorized reviewer to the evidence, and enforce separation across roles, teams, or trust domains.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nolane-x/forge-os/enforcing-review-separation
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 Nolane-x/forge-os --skill enforcing-review-separation
Clone the repo
git clone --depth 1 https://github.com/Nolane-x/forge-os

Made for: Claude Code.

Or install forgeos, the plugin that ships this one along with the rest of its 196 skills, 1 command, 1 agent, 1 MCP server.

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 enforcing-review-separation

README.md
[![agentmods](https://agentmods.dev/badge/skills/nolane-x/forge-os/enforcing-review-separation/github.svg)](https://agentmods.dev/skills/nolane-x/forge-os/enforcing-review-separation)
Your own site
<a href="https://agentmods.dev/skills/nolane-x/forge-os/enforcing-review-separation"><img src="https://agentmods.dev/badge/skills/nolane-x/forge-os/enforcing-review-separation/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 enforcing-review-separation

Your own site · 80×15
<a href="https://agentmods.dev/skills/nolane-x/forge-os/enforcing-review-separation"><img src="https://agentmods.dev/badge/skills/nolane-x/forge-os/enforcing-review-separation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 183 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 $0.00034 $0.00183
Opus 5 $0.00017 $0.00092
Sonnet 5 $0.00007 $0.00037
Haiku 4.5 $0.00003 $0.00018

Measured 9d ago against content hash 093e2e83c09a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

enforcing-review-separation 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 9d 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.

skills-v2/kernel/enforcing-review-separation/SKILL.md · 23 lines

What it actually says

Enforcing Review Separation

Core principle

Resolve producer, resolver, evaluator, closer, and signer trust domains. Bind the authorized reviewer and evidence set to the reviewed subject. The runtime owns deterministic scope, coverage, policy, and evidence checks; the agent owns only the judgment that cannot be reduced safely to code.

Do not activate when

  • A0 prototype policy explicitly permits self-review
  • the action is a reversible draft with no assurance claim
Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 23 lines · 34 tokens per session scan A 093e2e83c09a

Subscribe to this mod's changes

enforcing-review-separation is a skill published in the GitHub repository Nolane-x/forge-os (10 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 183 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.