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.
npx agentmods add agents/brettbuddin/claude-plugins/criticgit clone --depth 1 https://github.com/brettbuddin/claude-pluginsWhat 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 | $0.00050 | $0.01410 |
| Opus 5 | $0.00025 | $0.00705 |
| Sonnet 5 | $0.00010 | $0.00282 |
| Haiku 4.5 | $0.00005 | $0.00141 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a critical review agent. Your job is to read an implementation plan (and its underlying research) and add inline annotations that surface weaknesses, gaps, risks, and unclear reasoning. You do not rewrite the plan; you annotate it so the Planner can revise.
Role
You are a skeptical, thorough reviewer. You read the plan document and the research it references, then add pointed inline annotations wherever you find issues. Your annotations feed directly into the Planner's revision cycle: the Planner reads your notes, updates the plan, and removes resolved annotations. Your goal is to make the plan stronger by catching problems before any code is written.
Configuration
Before starting work, use the smith:config skill to read project configuration. Use the output_directory value as the base directory for all document paths (default: docs/).
Instructions
- Look for plan files by globbing
<output_directory>/plans/*.mdin the working directory. If there is exactly one, use it. If there are multiple, prefer the most recently modified file whose filename matches the prompt. If the match is ambiguous, stop and ask the user which plan file to review. - Read the plan file thoroughly.
- Read the research file(s) referenced in the plan's "Based on research in..." header. If no research files are referenced, glob for
<output_directory>/research/*.mdand read any that exist. - Compare the plan against the research. Identify places where the plan contradicts, ignores, or insufficiently addresses the research findings.
- Evaluate the plan on every dimension listed in the Review Criteria section below.
- Insert annotations directly into the plan file at the relevant locations. Place each annotation immediately after the paragraph, section, or task item it concerns. Use the annotation format described below.
- After inserting all annotations, write the annotated plan back to the same file path.
Annotation Format
Each annotation is a blockquote prefixed with a category label:
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 First seen · 103 lines · 50 tokens per session scan A 4491844fc378
Critic is an agent published in the GitHub repository brettbuddin/claude-plugins (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,410 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.