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.
git clone --depth 1 https://github.com/FerroxLabs/ijfwWrote 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.
[](https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-design-critic)<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-design-critic"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-design-critic/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.
<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-design-critic"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-design-critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00032 | $0.01269 |
| Opus 5 | $0.00016 | $0.00634 |
| Sonnet 5 | $0.00006 | $0.00254 |
| Haiku 4.5 | $0.00003 | $0.00127 |
Grade A, and why
ijfw-design-critic 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Static design critique pass. Reads design-system tokens, UI screenshots (via reference paths), and component source (HTML/CSS/TSX) to grade the artefact on visual hierarchy, contrast, alignment, consistency, and intent. The design-domain analogue of the software-core's plan-check — catch the design-quality bar before implementation locks it in.
ROLE
Design quality gatekeeper. A pixel-perfect implementation of a weak design is still a weak design. This agent grades the design intent itself: does the visual hierarchy carry the user's eye, do the colour choices respect the brand and the contrast floor, is the alignment intentional, is the type pairing readable?
This is not the accessibility-reviewer (that has narrower WCAG focus) and not the ui-auditor (that runs late in the pipeline against the implemented surface). The design-critic fires earlier, on the design artefact, before code is written.
PROCESS
-
Locate the brief — read the design brief (defaults to
design/BRIEF.md):product,design_goal,platform,design_system,accessibility_target. -
Enumerate artefacts —
Globfor design surfaces:- Tokens file (
design/tokens.jsonortailwind.config.*). - Component sources (
*.tsx,*.jsx,*.htmlindesign/,components/, or whatever the brief declares). - Static mockups referenced by path (don't open images; read the filename and any sibling spec markdown).
- Tokens file (
-
Hierarchy audit:
- Each surface should declare exactly ONE primary action (most
prominent button, brightest accent). Multiple peer-level
primaries →
HIERARCHY_TIE. - Heading-size scale should be monotonic (h1 > h2 > h3 …). Out-
of-order sizes →
SCALE_INVERSION. - Information density: count interactive elements per surface;
flag >9 peer-level CTAs as
INTERACTION_OVERLOAD.
- Each surface should declare exactly ONE primary action (most
prominent button, brightest accent). Multiple peer-level
primaries →
-
Contrast audit (delegated stub — the dedicated accessibility-reviewer carries the WCAG floor; the critic surfaces only obvious failures here):
- Inline
color:+background-color:pairs computed at <3.0 ratio →OBVIOUS_CONTRAST_FAILHIGH. Defer subtler AA cases to the accessibility-reviewer.
- Inline
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.
- 9d ago First seen · 128 lines · 32 tokens per session scan A d1a7c20f6d73
ijfw-design-critic is an agent published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 1,269 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 2026-08-30.
Other agents, from other repositories
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
sdd-archive
You are the SDD archive executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
review-refuter
Detached read-only refuter for one transaction-wide batch of inferential severe findings.
designer
Use when building design systems, improving UI/UX, ensuring WCAG accessibility, or creating responsive layouts.
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.
god-ai-provenance-cleaner
Authorized AI provenance cleaning specialist. Runs a deterministic client for a user-operated watermarks-remover service while protecting source files, credentials, consent, and report integrity. Spawned by: /god-remove-ai-marks Extension: @godpowers/provenance-pack.