agentmods.dev

ard-reviewer

ard-reviewer is an agent for Claude Code from ihudak/ihudak-claude-plugins. It costs 107 tokens per session (1,152 once invoked), scanned A, original, MIT.

A read-only reviewer for an Architecture Requirements/Decision Document, or ARD, which records important technical requirements and decisions. It checks the document against source files, inherited product requirements, formatting rules, and testable decision rules.

In plain words
What is it for?
Use it to review draft ARDs for accurate file references, valid decision statements, consistency with higher-level requirements, correct scope, and other documented quality rules.
Why use it?
Architecture documents can contain unsupported claims, contradictions, or decisions that cannot be tested. The review identifies these problems before the document is passed to the next stage.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the product-workflows plugin — 14 commands, 13 agents shipped together

not rated 2repo changed 2d ago A scan 107 tokens original MIT

Good fit Use it to review draft ARDs for accurate file references, valid decision statements, consistency with higher-level requirements, correct scope, and other documented quality rules.

Compare 6 agents from other repositories ↓
View source ↗ ihudak/ihudak-claude-plugins
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ihudak/ihudak-claude-plugins
Claude Code
/plugin install product-workflows

Made for: Claude Code.

Or install product-workflows, the plugin that ships this one along with the rest of its 14 commands, 13 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 ard-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/ard-reviewer/github.svg)](https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/ard-reviewer)
Your own site
<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/ard-reviewer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/ard-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 ard-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/ard-reviewer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/ard-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,152 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 $0.00107 $0.01152
Opus 5 $0.00053 $0.00576
Sonnet 5 $0.00021 $0.00230
Haiku 4.5 $0.00011 $0.00115

Measured 2d ago against content hash a60923dae03e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ard-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/product-workflows/agents/ard-reviewer.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Core references. A citation of the form workflows-core:<name> names a shared reference in the workflows-core plugin. Load it with Skill(skill: "workflows-core:reference", args: "<name>") — never by path: ${CLAUDE_PLUGIN_ROOT} resolves to this plugin, which does not carry it.

Read-only whole-ARD reviewer for drafts produced by /create-ard. Uses the strongest available reasoning model (Claude Opus). Reads the whole ARD and checks it against the rules in ${CLAUDE_PLUGIN_ROOT}/references/ard-format.md plus the dimensions below. Never edits the ARD.

Invoked from /create-ard Phase 5 after authoring. A BLOCK verdict gates the handoff — the caller runs a fix cycle and re-reviews once.

Input contract

  • ARD path — absolute path to the ARD (ard.md, or an area-scoped ard-<area>.md). Required; if absent, stop and report.
  • Scope — prd | epic. Review at the stated altitude; for an Epic-level ARD also read the inherited PRD-level ARD named in inherits: (if any) to check for contradictions.

Review method

  1. Read the ARD end-to-end before judging.
  2. Verify frontmatter: scope; prd matches ^[A-Z][A-Z0-9_]*(-\d+)+$ — the grammar workflows-core:addressing §1 fixes, a superset of the two-segment form, so that an ARD authored by /create-ard on the BRD route carries a well-formed key rather than a finding: on that route prd holds a BRD key (the BRD's own, or its parent's for a slice) and epic holds the slice's, either of which may carry a third numeric segment; grounded_repos present; Epic-level has epic + (if a PRD-level ARD exists) inherits. derived_from names the PRD the ARD was built from, or — on the BRD route, in a folder that holds no PRD — the ard-seed.md it was actually authored from; neither is a finding.
  3. For each "as-is" claim in Grounding findings, confirm it cites a file:line in a grounded_repos entry — spot-check that the cited path plausibly exists (Glob/Grep). An uncited or clearly-fabricated claim → BLOCKER.
  4. Apply the dimensions below; record findings in the severity schema; route gaps needing human input to needs architect input; never fabricate a fix.

Read the full file on GitHub · 54 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.

  1. 2d ago Changed · +2 lines a60923dae03e
  2. 5d ago Changed f53491ce72ee
  3. 10d ago First seen · 52 lines · 107 tokens per session scan A 6496aaf3e21b

Subscribe to this mod's changes

ard-reviewer is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 1,152 once invoked, about $0.0005 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.

Claude CodeCode reviewPlanningai-agentsai-code-reviewclaude-code-pluginsdeveloper-productivitydocumentation-automation
Related

Other agents, from other repositories

code-reviewer

Reviews all changed files in a change set in an isolated context and returns structured findings as JSON. Spawned by the /review-gate:review orchestrator. Not for general questions.

Jose-Ribeir/claude-code-review-gate · 41 tokens

code-filter

Independent falsify pass for review-gate findings. Receives unified diffs + a findings list and returns the IDs of findings to drop. Spawned by the /review-gate:review orchestrator after the code-reviewer. Not for general questions.

Jose-Ribeir/claude-code-review-gate · 54 tokens

code-reviewer

Expert code review specialist. Use proactively after writing or modifying code to check quality, security, and maintainability.

boshu2/agentops · 26 tokens

reviewer

Review changes against spec, plan, code quality heuristics, and repo rules. Supports local (ADOS pipeline) and remote (PR/MR) modes.

juliusz-cwiakalski/agentic-delivery-os · 34 tokens

adversarial-reviewer

Adversarial reviewer for specs, plans, implementations, or any combination ("spec amendment + implementation in the same PR" is the dominant case). Loads project conventions and the targeted artifacts; attacks along the relevant checklists; returns severity-labeled findings. Use after gates pass but before declaring…

eugenelim/agent-ready-repo · 97 tokens

quality-engineer

Quality-lens reviewer covering testability, observability, reliability, and maintainability -- the "cost to live with this code" pass. Also drafts contract or construction tests on request. Reads effective repository guidance, the spec and plan if any, the diff, and nearby tests; flags test-shape problems (wrong…

eugenelim/agent-ready-repo · 172 tokens