guideline-reviewer

guideline-reviewer is a command for Claude Code from ihudak/ihudak-claude-plugins. It costs 45 tokens per session (617 once invoked), scanned A, original, MIT.

A test runner that records the results of a project's full test suite and compares later runs with that record. A baseline is the starting result used for comparison.

In plain words
What is it for?
Use capture before making changes, then verify afterward to produce a structured regression report.
Why use it?
It shows whether code changes introduced new test failures or changed existing results.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Part of the guideline-reviewers plugin — 2 commands, 2 agents shipped together

Good fit Use capture before making changes, then verify afterward to produce a structured regression report.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ihudak/ihudak-claude-plugins/guideline-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/ihudak/ihudak-claude-plugins

Made for: Claude Code.

Or install guideline-reviewers, the plugin that ships this one along with the rest of its 2 commands, 2 agents.

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 guideline-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/guideline-reviewer/github.svg)](https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/guideline-reviewer)
Your own site
<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.

agentmods 80×15 button for guideline-reviewer

Your own site · 80×15
<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>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 617 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 $0.00045 $0.00617
Opus 5 $0.00023 $0.00309
Sonnet 5 $0.00009 $0.00123
Haiku 4.5 $0.00005 $0.00062

Measured 2d ago against content hash a3d58ec1490d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

plugins/guideline-reviewers/commands/guideline-reviewer.md · 29 lines

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 Check section: detect the target repo's own eslint-plugin-jsx-a11y configuration 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 ruleId and W3C ACT rule id from references/guidelines/accessibility.md alongside 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 Overlay section and open the report with the rules_source: and a11y_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.

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. 2d ago Changed a3d58ec1490d
  2. 11d ago First seen · 29 lines · 45 tokens per session scan A fdf75a8c9c7d

Subscribe to this mod's changes

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.