review

review is a skill for Claude Code from william-london/ownframework-loop. It costs 35 tokens per session (495 once invoked), scanned A, original, Apache-2.0.

A controlled review step in OwnFramework Loop that checks a completed build against its exact source revision.

In plain words
What is it for?
Use it to re-check the submitted work packet, claim a review pass, prepare the review, and stop or wait when the workflow is not ready.
Why use it?
It prevents review from starting before there is a build record and keeps review state changes tied to the correct code and workflow rules.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Part of the of-loop plugin — 5 skills, 2 agents, 2 hooks shipped together

Good fit Use it to re-check the submitted work packet, claim a review pass, prepare the review, and stop or wait when the workflow is not ready.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/william-london/ownframework-loop/of-loop-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 william-london/ownframework-loop --skill of-loop-review
Clone the repo
git clone --depth 1 https://github.com/william-london/ownframework-loop

Made for: Claude Code.

Or install of-loop, the plugin that ships this one along with the rest of its 5 skills, 2 agents, 2 hooks.

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 review

README.md
[![agentmods](https://agentmods.dev/badge/skills/william-london/ownframework-loop/of-loop-review/github.svg)](https://agentmods.dev/skills/william-london/ownframework-loop/of-loop-review)
Your own site
<a href="https://agentmods.dev/skills/william-london/ownframework-loop/of-loop-review"><img src="https://agentmods.dev/badge/skills/william-london/ownframework-loop/of-loop-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 review

Your own site · 80×15
<a href="https://agentmods.dev/skills/william-london/ownframework-loop/of-loop-review"><img src="https://agentmods.dev/badge/skills/william-london/ownframework-loop/of-loop-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 495 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 $0.00035 $0.00495
Opus 5 $0.00017 $0.00247
Sonnet 5 $0.00007 $0.00099
Haiku 4.5 $0.00003 $0.00049

Measured 8d ago against content hash cd34dbaaeee5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • review — 94% identical, 3 lines differ
.agents/skills/of-loop-review/SKILL.md · 58 lines

What it actually says

/of-loop:review - one bounded review pass

The parent is a thin coordinator. It does not engineer source and does not own branch/worktree/state identity.

Fast paths (single source of truth)

State Action
APPROVED / BLOCKED / STOPPED STOP
AWAITING_APPROVAL / READY_TO_START WAIT - builder owns first start
READY_TO_BUILD / BUILDING / CHANGES_REQUESTED WAIT - no reviewable receipt yet
READY_FOR_REVIEW / replayed REVIEWING REVIEW - proceed

Pre-start semantics

For an unstarted run with state AWAITING_APPROVAL / READY_TO_START:

  • Reviewer WAITS. The builder owns first execution start.
  • Reviewer does NOT create the execution seal independently.
  • Reviewer does NOT call ofloop build claim.
  • Reviewer does NOT issue approval or token.

After the builder creates a build receipt and transitions state to READY_FOR_REVIEW or CHANGES_REQUESTED, the reviewer proceeds with normal exact-SHA review.

Pass responsibilities

  1. Re-prove current packet bytes and execution binding.
  2. Claim via ofloop review claim --actor reviewer. A replayed REVIEWING claim is the same pass and MUST NOT increment budget.
  3. Run ofloop review prepare .
  4. Optionally materialize reviewer scratch via ofloop review assessment-skeleton.
  5. Run ofloop review finalize .
  6. Emit ofloop review marker .

Prohibitions

No raw worktree creation or removal; no direct state/receipt/verdict writes; no scope/budget widening; no push, merge, deploy, publish, remote creation, or external effect.

Scheduling

Canonical unattended scheduling is ofloop supervisor enqueue <repo> <run-id>. This skill represents one pass and may be invoked through a host adapter for foreground/debug work. It is not the durable execution clock.

The operator supplies no cadence, claim, preparation, assessment-skeleton, finalizer, or approval commands.

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. 8d ago First seen · 58 lines · 35 tokens per session scan A cd34dbaaeee5

Subscribe to this mod's changes

review is a skill published in the GitHub repository william-london/ownframework-loop (0 stars, last pushed 6d ago), licensed Apache-2.0. It adds 35 tokens to every session and 495 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.