A review workflow for finding and recording problems in code changes, documents, designs, or other project artifacts, with severity labels and suggested fixes.

It is for reviewing pull requests, diffs, book chapters, campaign briefs, landing-page copy, design tokens, and similar work.

It turns a broad review into clear, prioritised findings that can be fixed before release.

ijfw-review — Skill for Claude Code by FerroxLabs

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 FerroxLabs/ijfw --skill ijfw-review

Clone the repo

git clone --depth 1 https://github.com/FerroxLabs/ijfw

Made for: Claude Code.

Or install ijfw, the plugin that ships this one along with the rest of its 34 skills, 22 commands, 37 agents, 6 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-review/github.svg)](https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-review)

Your own site

<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-review"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-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/ferroxlabs/ijfw/ijfw-review"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,255 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high System Prompt Leakage · line 53
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.

How audits are shown

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	$0.00065	$0.01255
Opus 5	$0.00032	$0.00628
Sonnet 5	$0.00013	$0.00251
Haiku 4.5	$0.00006	$0.00126

Measured 6d ago against content hash 7502f43f1f3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ijfw-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 6d 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.

claude/skills/ijfw-review/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Domain-agnostic critique. One-line findings, severity-tagged, with a written REVIEW.md artifact.

Severity vocabulary (all domains)

BLOCK -- must-fix before ship. Bug, data loss, broken claim, factual error, WCAG violation, missing CTA.
FLAG -- should discuss. Risky choice, weak evidence, voice break, ambiguous audience, fragile coupling.
NIT -- polish. Phrasing, micro-spacing, naming, redundancy.

Format per finding: <LOC>: [SEVERITY] <one-line problem>. <one-line fix>. <LOC> is file:line for code, <section> or <page> for prose/design.

Domain checklists

Software (code diff / PR)

Null & undefined handling, error paths, retry/backoff semantics.
Security boundaries: input validation, authz, secret leakage, path traversal.
Test coverage: happy path + at least one failure case per public surface.
Concurrency: race conditions, idempotency, ordering assumptions.
Public API: backward compatibility, types, naming.

Book chapter

Continuity with prior chapters (character state, world facts, timeline).
Voice / POV consistency.
Pacing: scene-vs-summary ratio, dwell on stakes.
Character beats: motivation legible, agency visible.
Stakes: what is at risk on this page, why now.

Campaign brief

Audience: named, specific, has a current alternative.
Message-to-channel fit: format matches where the audience already is.
CTA: single, frictionless, measurable.
KPI coverage: leading + lagging indicator named.
Kill criteria: the condition under which you stop spending.

Landing page (copy + layout)

Promise -> proof -> CTA alignment in the first viewport.
Mobile-readiness: tap targets >= 44px, no horizontal scroll, hero readable at 375px.
Accessibility: WCAG AA contrast 4.5:1 body / 3:1 large text; alt text on meaningful images; keyboard reachable CTA.
Conversion-path friction: number of decisions before primary CTA.

Design artifact (tokens / mockup)

Token consistency: every color/space/radius/shadow resolves to a defined token.
Contrast: WCAG AA on every text-on-surface pair.
Type scale: modular ratio respected; no orphan sizes.
Spacing rhythm: 4/8 baseline (or declared grid) respected.

Read the full file on GitHub · 121 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.

6d ago First seen · 121 lines · 65 tokens per session scan A 7502f43f1f3d

Subscribe to this mod's changes

ijfw-review is a skill published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 1,255 once invoked, about $0.0003 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 2026-09-05.

Claude Code Code review ai-agents ai-coding codex cursor developer-tools

sdd-apply

Skill "sdd-apply" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, purpose, what you receive and execution and persistence contract.

Gentleman-Programming/gentle-ai · 0 tokens

gentle-ai-collab-perfect

Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…

Gentleman-Programming/gentle-ai · 106 tokens

ijfw-review