dancing-bear: Skill for Claude Code

.claude/skills/review-fix-threads/SKILL.md

review-fix-threads is a skill for Claude Code from dancing-bear-show/dancing-bear. It costs 83 tokens per session (2,453 once invoked), scanned A, original, MIT.

An automated helper for handling review threads on a pull request, which is a proposed set of code changes awaiting review. It reads comments from people and Copilot, fixes applicable issues, checks the changes, replies to every thread, and resolves them.

In plain words
What is it for?
Use it after a pull request already has review comments. It can triage the comments, make fixes in parallel, test both expected and error cases, update the pull request title and description, and close out the threads.
Why use it?
It removes the manual work of tracking many review comments and confirming that each one was addressed. Failed tests, lint checks, or coverage checks stop it before it posts replies or resolves threads.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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/skills/review-fix-threads/SKILL.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 review-fix-threads

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/dancing-bear-show/dancing-bear/review-fix-threads"><img src="https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/review-fix-threads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,453 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 $0.00083 $0.02453
Opus 5.5 $0.00033 $0.00981
Sonnet 5.5 $0.00017 $0.00491
Haiku 4.5 $0.00008 $0.00245

Measured yesterday against content hash e93b77f5684e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-fix-threads 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/skills/review-fix-threads/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review, Fix, and Resolve PR Threads

Delegates to workflows/code/review-fix-threads.yaml. Runs unattended from "here is a PR" to "every thread has a reply and is resolved".

When to Use

  • A PR has Copilot and/or human review threads waiting on the author
  • The user says "address the feedback", "fix the review comments", "resolve the threads"
  • Feedback has already been reviewed and now needs remediation

Use /code-review instead when the PR needs reviewing — this skill consumes review threads that already exist, it does not produce them.

Autonomy

There is no human gate. The workflow posts replies and resolves threads without confirmation, including on threads it decided not to action — a rejected or moot thread gets a reply explaining why, then is resolved.

What constrains it:

  • verify-fixes reports itself failed and exits non-zero when tests, lint, or coverage are not green, which halts the run before anything is posted.
  • resolve-threads re-checks all_green itself and fails closed: a missing, unparseable, or ambiguous verification file aborts the stage. It reads the path from resolve-plan.json's verify_file rather than guessing, since the two callers of that fragment keep the file in different places and a hardcoded path would silently find nothing for one of them.
  • plan-resolution will not compose replacement prose at the moment of posting: a missing replies file produces an empty plan and a non-zero exit.
  • A reply always posts before its thread resolves. A resolve whose reply failed is skipped and reported.
  • Threads whose fixer crashed, or whose fix was never tested, are never resolved and never receive a reply claiming a fix.
  • context and defer threads are never resolved — including threads deferred by the max_threads ceiling, since that is a scheduling outcome rather than a judgement about the comment.
  • Every rejection is recorded with evidence in the final report, so the calls made on your behalf can be audited after the fact.

Read the full file on GitHub · 193 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 · 193 lines · 83 tokens per session scan A e93b77f5684e

Subscribe to this mod's changes

review-fix-threads is a skill published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 2,453 once invoked, about $0.0003 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

review-fix-threads compared with skills from other repositories

review-fix-threads next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
review-fix-threadsdancing-bear-show/dancing-bearSkill7yesterdayMITA83Claude Code
gogolafkfreund/nixos_configSkill32yesterdayGPL-3.0A125Claude Code, Codex
google-workspace-authbobmatnyc/claude-mpmSkill1582mo agononeA22Claude Code
find-simplificationsQwenLM/qwen-codeSkill29ktodayApache-2.0C103Claude Code, Codex
swarm-pr-reviewZaxbyHub/opencode-swarmSkill518todayMITA91Claude Code
code-reviewjrswab/axeSkill90917d agoApache-2.0A0Claude Code, Codex
agent-debug-ciNVIDIA/elementsSkill115yesterdayApache-2.0A80Claude Code, Codex