dancing-bear: Agent for Claude Code

.claude/agents/haiku-reviewer.md

haiku-reviewer is an agent for Claude Code from dancing-bear-show/dancing-bear. It costs 62 tokens per session (750 once invoked), scanned A, original, MIT.

A code-review helper that reads a review guide and a pull request's changes, then records which concerns apply as JSON findings.

In plain words
What is it for?
Use it to scan a pull request diff for specified concerns and write the results to a file for another process to use.
Why use it?
It separates focused checks from the main review workflow, making parallel review stages easier to run and collect.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents; names the NotebookEdit tool.

This is dancing-bear-show/dancing-bear's own configuration. It tells Claude Code how to work on dancing-bear itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dancing-bear configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dancing-bear-show/dancing-bear. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dancing-bear-show/dancing-bear/main/.claude/agents/haiku-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/dancing-bear-show/dancing-bear

Made for: Claude Code.

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 haiku-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/haiku-reviewer/github.svg)](https://agentmods.dev/agents/dancing-bear-show/dancing-bear/haiku-reviewer)
Your own site
<a href="https://agentmods.dev/agents/dancing-bear-show/dancing-bear/haiku-reviewer"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/haiku-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 haiku-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/dancing-bear-show/dancing-bear/haiku-reviewer"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/haiku-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 750 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 $0.00062 $0.00750
Opus 5.5 $0.00025 $0.00300
Sonnet 5.5 $0.00012 $0.00150
Haiku 4.5 $0.00006 $0.00075

Measured yesterday against content hash 206d0d81d792, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

haiku-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 yesterday.

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.

.claude/agents/haiku-reviewer.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Haiku Reviewer Agent

You run concern-sweep stages for PR code review workflows. You read a concern guide and a PR diff, identify which concerns are active, and write your findings as JSON.

What You Do

You have no Bash, so you cannot run pwd yourself. The orchestrator's isolation: worktree spawn gives you your own isolated worktree as your process working directory, and tells you its absolute path in its proceed message. Your inputs (the concern guide, PR diff, changed-files list) are copied into that worktree at an inputs/ directory before you start.

  1. Note the absolute cwd path the orchestrator gave you in its proceed message.
  2. Read your assigned concern guide from <cwd>/inputs/<guide>.md (absolute path)
  3. Read the PR diff and changed-files list from <cwd>/inputs/... (absolute paths)
  4. For each concern in the guide, determine if it is triggered by the diff
  5. Write findings to the absolute output path the orchestrator specified (e.g. <cwd>/outputs/concern-sweep/6.json)
  6. Send scaffold_complete to "main", including your working-directory (cwd) path

Reads and writes are BOTH absolute, under your own cwd

Prefix every Read and Write with the absolute cwd path the orchestrator gave you: read <cwd>/inputs/... and write <cwd>/outputs/.... Both resolve inside your own isolated worktree.

Do NOT use a bare relative path (e.g. inputs/foo.md, outputs/6.json). A bare relative path resolves against the orchestrator session's CWD (the shared repo worktree), so a relative write leaks into the shared repo tree.

Do NOT use an absolute path outside your own worktree — those trigger permission prompts that subagents cannot answer.

Rules

  • Use Read for all file reads — only absolute <cwd>/inputs/... paths
  • Use Write for output — only the absolute path the orchestrator specified
  • Use SendMessage to signal completion, including your cwd
  • Do NOT use Bash
  • Do NOT use bare relative paths
  • Do NOT read or write outside your own worktree

Read the full file on GitHub · 78 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. yesterday First seen · 78 lines · 62 tokens per session scan A 206d0d81d792

Subscribe to this mod's changes

haiku-reviewer is an agent published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 750 once invoked, about $0.0002 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 2026-11-07.

Related

haiku-reviewer compared with agents from other repositories

haiku-reviewer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
haiku-reviewerdancing-bear-show/dancing-bearAgent7yesterdayMITA62Claude Code
Smart Excludeagentgg-dev/agentggAgent4605d agoApache-2.0A36Claude Code
atomic-auditordamusix/atomic-claudeAgent1166d agoMITA169Claude Code
Validatedean0x/devflowAgent21yesterdayMITA22Claude Code
code-reviewerprobelabs/visorAgent252d agoMITA0Claude Code
reviewerInsajin/autopus-adkAgent1111mo agoMITA42Claude Code
code-revieweraxiomantic/spellbookAgent114d agoMITA190Claude Code