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/ihudak/ihudak-claude-pluginsWrote 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/commands/ihudak/ihudak-claude-plugins/guideline-reviewer)<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/guideline-reviewer"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/guideline-reviewer/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/commands/ihudak/ihudak-claude-plugins/guideline-reviewer"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/guideline-reviewer.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 | $0.00045 | $0.00617 |
| Opus 5 | $0.00023 | $0.00309 |
| Sonnet 5 | $0.00009 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
guideline-reviewer 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 2d 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.
What it actually says
Review app code and UI for compliance with public UI design-system and accessibility standards: $ARGUMENTS
If $ARGUMENTS is empty, ask the user which files or components to review.
--rules <path> (optional) — an organization's own UI rule directory, layered over the bundled baseline. Set it aside from $ARGUMENTS before resolving the files to review, and pass it to the agent as rules_path. Absent, the agent resolves an overlay itself from <repo-root>/.dev-workflows/ui-guidelines/ then $UI_GUIDELINES_PATH, falling back silently to the bundled baseline.
Dispatch the review to the guideline-reviewer subagent:
→ Agent (subagent_type: "guideline-reviewers:guideline-reviewer"):
"Review the following app code and UI for compliance with public UI design-system and accessibility standards: $ARGUMENTS
Run the deterministic accessibility check first, per your
## Deterministic Accessibility Checksection: detect the target repo's owneslint-plugin-jsx-a11yconfiguration and, if it is configured, run the repo's own lint scoped to the files under review; otherwise detect a runtime axe harness (jest-axe,cypress-axe,@axe-core/playwright,@axe-core/cli) and record it WITHOUT running it — a review has no rendered app. Neither configured ⇒ skip silently and review as normal. Never install anything, never prompt, never fail the run over missing tooling.Merge the linter's findings rather than duplicating them: a finding it reported deterministically is not re-raised by your review pass. Cite the axe-core
ruleIdand W3C ACT rule id fromreferences/guidelines/accessibility.mdalongside the WCAG success criterion on every accessibility finding that has one, and never invent an id.rules_path: [the --rules value, or omit]
Resolve the rule overlay per your
## Rule Overlaysection and open the report with therules_source:anda11y_check:lines (eslint-jsx-a11y|harness-detected:<name>|none)."
Surface the subagent's verdict to the user, including its a11y_check: line and, when a runtime harness was detected, its statement that the harness was not executed. Never restate a detected-but-unrun harness as a check that ran.
a11y_check: none is a normal outcome, not a problem to report: mention it once as the recorded value and do not suggest the user install tooling.
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.
- 2d ago Changed a3d58ec1490d
- 11d ago First seen · 29 lines · 45 tokens per session scan A fdf75a8c9c7d
guideline-reviewer is a command published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 617 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.
Other commands, from other repositories
pi-ui-review
UI/UX review via Gemini — accessibility, responsive design, component structure.
design
Generate and update visual design assets per the project's design system.
frankx-infogenius
Premium-First Image Generation - Research → Brand-Aligned Style → High-Quality Output.
pi-ui-design
HTML mockup generation via Gemini — from design spec to previewable prototype.
frankx-ai-components
Create and update UI components for FrankX.AI with glassmorphic design system.
design-intent
Guided UI/visual development with structured exploration, architecture design, and quality review.