review-resolver

review-resolver is a skill for Claude Code, Codex from kBashar/myagentskills. It costs 82 tokens per session (1,272 once invoked), scanned A, original, Apache-2.0.

A workflow for reviewing comments on a GitHub pull request, which is a proposed code change awaiting review. It checks each comment against the actual code, lets you choose what to address, and verifies the selected fixes.

In plain words
What is it for?
Use it to inspect a pull request, investigate reported problems, choose comments to resolve, implement the selected changes, and confirm they are fixed.
Why use it?
It turns scattered review feedback into an ordered set of decisions and prevents changes based on misunderstandings or comments you did not approve.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; names the AskUserQuestion tool.

Good fit Use it to inspect a pull request, investigate reported problems, choose comments to resolve, implement the selected changes, and confirm they are fixed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kbashar/myagentskills/review-resolver
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.

Any agent
npx skills add kBashar/myagentskills --skill review-resolver
Clone the repo
git clone --depth 1 https://github.com/kBashar/myagentskills

Made for: Claude Code, Codex.

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-resolver

README.md
[![agentmods](https://agentmods.dev/badge/skills/kbashar/myagentskills/review-resolver.svg)](https://agentmods.dev/skills/kbashar/myagentskills/review-resolver)
Your own site
<a href="https://agentmods.dev/skills/kbashar/myagentskills/review-resolver"><img src="https://agentmods.dev/badge/skills/kbashar/myagentskills/review-resolver.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,272 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 $0.00082 $0.01272
Opus 5 $0.00041 $0.00636
Sonnet 5 $0.00016 $0.00254
Haiku 4.5 $0.00008 $0.00127

Measured 8d ago against content hash 94aca39661c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-resolver 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 8d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/fetch-comments.sh, scripts/preflight.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

review-resolver/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

review-resolver

Overview

Turn a PR's scattered review feedback into resolved code, safely and auditably. The flow is: gate the worktree → fetch all comments → investigate each in real code → present a triage table → resolve what the operator selects → verify resolution.

Core principle: investigate before judging, and let the operator decide what to fix. Never resolve a comment you haven't traced into the actual code, and never fix comments the operator didn't select.

Inputs

A GitHub PR URL (https://github.com/owner/repo/pull/123) or a bare number 123. A bare number resolves against the git repo in the current directory. The target project repo — where the code lives — must be the current directory (or pass its path as the second script argument).

Workflow

Create one todo per step.

Step 1 — Preflight: clean-tree gate + checkout (automated)

A clean git tree is a prerequisite. Run:

scripts/preflight.sh <pr-number-or-url> [repo-dir]
  • Exit 3 = dirty worktree. STOP. Show the operator the printed git status and tell them to commit, stash, or discard. Do NOT proceed, do NOT stash on their behalf without being asked.
  • Exit 2 = not a git repo (wrong directory).
  • Exit 0 = tree was clean and the PR branch is now checked out. Continue.

Step 2 — Fetch all comments (automated)

scripts/fetch-comments.sh <pr-number-or-url> [repo-dir]

Emits one JSON array covering all three GitHub feedback channels — inline (line-level code comments, with path+line+diff_hunk), review (summary bodies + verdict state), and issue (general conversation). Save it (e.g. to the scratchpad) and parse it. Thread replies via in_reply_to.

Filter out noise before triaging: skip nitpick/approval-only chatter and bot comments unless they raise a real concern. Keep every substantive comment.

Step 3 — Investigate each comment in the real code

For each substantive comment, do not take it at face value:

Read the full file on GitHub · 93 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 93 lines · 82 tokens per session scan A 94aca39661c7

Subscribe to this mod's changes

review-resolver is a skill published in the GitHub repository kBashar/myagentskills (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 82 tokens to every session and 1,272 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

verify-behavior

Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…

nicknisi/dotfiles · 68 tokens

github-contributor

End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…

daymade/claude-code-skills · 133 tokens

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens

write-pr

Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.

tldraw/tldraw · 53 tokens