agentmods.dev

critic

critic is an agent for Claude Code from jiutuhky/my-super-capsule. It costs 170 tokens per session (2,595 once invoked), scanned A, original, MIT.

A review agent for generated diagrams and charts. It compares an image with the source text or data and the description used to create it.

In plain words
What is it for?
Use it to review PaperBanana pipeline output and produce structured feedback or a revised figure description.
Why use it?
It finds mismatches or unclear parts in a generated figure before the figure is used.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the paper-banana plugin — 1 skill, 1 command, 5 agents shipped together

not rated 11repo +1 8mo ago A scan 170 tokens original MIT

Good fit Use it to review PaperBanana pipeline output and produce structured feedback or a revised figure description.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jiutuhky/my-super-capsule/critic
View source ↗ jiutuhky/my-super-capsule
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/jiutuhky/my-super-capsule

Made for: Claude Code.

Or install paper-banana, the plugin that ships this one along with the rest of its 1 skill, 1 command, 5 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 critic

README.md
[![agentmods](https://agentmods.dev/badge/agents/jiutuhky/my-super-capsule/critic/github.svg)](https://agentmods.dev/agents/jiutuhky/my-super-capsule/critic)
Your own site
<a href="https://agentmods.dev/agents/jiutuhky/my-super-capsule/critic"><img src="https://agentmods.dev/badge/agents/jiutuhky/my-super-capsule/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.

agentmods 80×15 button for critic

Your own site · 80×15
<a href="https://agentmods.dev/agents/jiutuhky/my-super-capsule/critic"><img src="https://agentmods.dev/badge/agents/jiutuhky/my-super-capsule/critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 170 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,595 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 $0.00170 $0.02595
Opus 5.5 $0.00068 $0.01038
Sonnet 5.5 $0.00034 $0.00519
Haiku 4.5 $0.00017 $0.00260

Measured 2mo ago against content hash 54637cefc196, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

paper-banana/agents/critic.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Critic Agent in the PaperBanana multi-agent pipeline.

Your Task

Critique a generated figure (diagram or plot) by comparing it against the source content and the detailed description used to generate it. Provide structured feedback and a revised description if improvements are needed.

File-Based Storage Convention

In this pipeline, descriptions, suggestions, and images are stored as separate files in subdirectories under output_dir. Keys in pipeline_state.json contain relative file paths (relative to output_dir). To read content, construct the absolute path: {output_dir}/{relative_path}. When writing new content, write to files in the appropriate subdirectory and store only the relative path in pipeline_state.json.

Step-by-Step Instructions

  1. Read pipeline_state.json to get:

    • task_type ("diagram" or "plot")
    • current_critic_round (0, 1, or 2)
    • content (methodology section or raw data — stored inline)
    • visual_intent (figure caption or plot intent — stored inline)
    • output_dir (absolute path to the output directory)
    • The relevant description and image path keys (see Round Logic below) — these are relative file paths

  2. Determine which description and image to critique (see Round Logic).

  3. Read the description text from the file at {output_dir}/{description_relative_path}.

  4. Read the generated image file at {output_dir}/{image_relative_path} using the Read tool (it supports images).

  5. Apply the appropriate system prompt (see below) and generate the critique.

  6. Parse the JSON output and write results to files:

    • Write critic suggestions to {output_dir}/descriptions/critic_suggestions{round_idx}.txt
    • Write revised description to {output_dir}/descriptions/critic_desc{round_idx}.txt

  7. Update pipeline_state.json with the relative file paths.

Round Logic

Round 0 (First critique):

  • Description key: target_{task_type}_stylist_desc0
  • Image path key: target_{task_type}_stylist_desc0_image_path

Read the full file on GitHub · 209 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. 2mo ago First seen · 209 lines · 170 tokens per session scan A 54637cefc196

Subscribe to this mod's changes

critic is an agent published in the GitHub repository jiutuhky/my-super-capsule (11 stars, last pushed 8mo ago), licensed MIT. It adds 170 tokens to every session and 2,595 once invoked, about $0.0007 per session on Opus 5.5. 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.

Creative and mediaDesign and UX
Related

critic compared with agents from other repositories

critic next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
criticjiutuhky/my-super-capsuleAgent118mo agoMITA170Claude Code
ux-flow-auditorCharlesWiltgen/AxiomAgent1.3kyesterdayMITA43Claude Code
canvas-create-screensmicrosoft/power-platform-skillsAgent1.1kyesterdayMITA24Claude Code
nw-ux-designernWave-ai/nWaveAgent631yesterdayMITA31Claude Code
designRune-kit/runeAgent882mo agoMITA35Claude Code
mobile-ux-optimizerxbim08/awesome-claude-code-pluginsAgent101mo agoApache-2.0A0Claude Code
visual-reviewermukiwu/muki-ai-pluginsAgent7415d agononeA52Claude Code