claude-code-history-viewer: Command for Claude Code

.claude/commands/pr-review-check.md

pr-review-check is a command for Claude Code from jhlee0409/claude-code-history-viewer. It costs 17 tokens per session (6,071 once invoked), scanned A, original, MIT.

A command for reviewing AI-generated pull-request comments, sorting valid issues from invalid ones, and fixing approved issues one at a time.

In plain words
What is it for?
Use it to collect review comments, assess their impact, produce a triage report, obtain approval, make focused fixes, and reply to reviewers in English.
Why use it?
It prevents unreviewed suggestions or broad automatic edits from changing code without the user's approval.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool; mentions Codex.

This is jhlee0409/claude-code-history-viewer's own configuration. It tells Claude Code how to work on claude-code-history-viewer 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 claude-code-history-viewer configures →

About the project

Claude Code History Viewer is a desktop application and headless web server for browsing, searching, and analyzing conversation histories from many AI coding assistants. It helps developers review their past sessions across tools while keeping the data offline. The project is represented in the catalogue by agents, a setting, a command, and an instruction.

jhlee0409/claude-code-history-viewer · 2,155 stars · on GitHub · jhlee0409.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to jhlee0409/claude-code-history-viewer. 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/jhlee0409/claude-code-history-viewer/main/.claude/commands/pr-review-check.md
Clone the repo
git clone --depth 1 https://github.com/jhlee0409/claude-code-history-viewer

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 pr-review-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/jhlee0409/claude-code-history-viewer/pr-review-check/github.svg)](https://agentmods.dev/commands/jhlee0409/claude-code-history-viewer/pr-review-check)
Your own site
<a href="https://agentmods.dev/commands/jhlee0409/claude-code-history-viewer/pr-review-check"><img src="https://agentmods.dev/badge/commands/jhlee0409/claude-code-history-viewer/pr-review-check/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 pr-review-check

Your own site · 80×15
<a href="https://agentmods.dev/commands/jhlee0409/claude-code-history-viewer/pr-review-check"><img src="https://agentmods.dev/badge/commands/jhlee0409/claude-code-history-viewer/pr-review-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,071 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 $0.00017 $0.06071
Opus 5 $0.00009 $0.03036
Sonnet 5 $0.00003 $0.01214
Haiku 4.5 $0.00002 $0.00607

Measured 11d ago against content hash 7e90848c1a5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pr-review-check 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 11d 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.

.claude/commands/pr-review-check.md · 429 lines

How it starts

The opening of the file, as written. The whole thing — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR 리뷰 코멘트 확인

AI 리뷰어(CodeRabbit, Claude bot, Codex, Gemini, Copilot 등)가 남긴 코멘트를 수집 · 분류 · 영향 분석 후, 승인된 유효 이슈만 한 건씩 원자적으로 수정한다.

Absolute rules (MUST follow):

  • MUST produce the triage report and get user approval BEFORE modifying any code.
  • MUST NOT copy-paste AI-suggested patches verbatim. Understand the concern, then re-derive the fix from scratch.
  • MUST fix one issue at a time. NO drive-by refactors, formatting changes, or style cleanups.
  • MUST write GitHub replies in English (user preference).
  • MUST NOT auto-resolve review threads. Let the reviewer (or the bot's re-review) close them.
  • MUST NOT invoke adversarial CLIs (gemini/codex) without explicit user approval.

입력 인자: $ARGUMENTS (PR 번호, 생략 가능)


Phase 0 — 수집 (Collect)

  1. PR 번호 결정: 인자가 있으면 사용, 없으면 gh pr view --json number -q .number 로 현재 브랜치의 PR 확인. PR이 없으면 사용자에게 물어본다.
  2. 리뷰 데이터 fetch (REST + GraphQL 조합):
    • gh api repos/{owner}/{repo}/pulls/{N}/comments — 인라인 코멘트
    • gh api repos/{owner}/{repo}/pulls/{N}/reviews — 리뷰 레벨 body
    • GraphQL로 review threads + resolution 상태:
      gh api graphql -f query='
        query($owner:String!,$repo:String!,$num:Int!){
          repository(owner:$owner,name:$repo){
            pullRequest(number:$num){
              reviewThreads(first:100){nodes{
                id isResolved isOutdated
                comments(first:20){nodes{id databaseId author{login} body path line originalLine diffHunk}}
              }}
            }
          }
        }' -f owner=... -f repo=... -F num=...
      
  3. AI 봇 필터: author login이 coderabbitai, coderabbitai[bot], claude[bot], chatgpt-codex-connector, gemini-code-assist[bot], copilot-pull-request-reviewer[bot], github-actions[bot] 중 하나인 것만. 인간 리뷰어 코멘트는 이 워크플로우 대상 아님 — 별도로 보고.
  4. resolved/outdated 스레드 제외 (이미 대응 완료).
  5. PR의 변경 파일 목록도 같이 확보: gh pr diff {N} --name-only — "in-scope" 판정에 사용.

Phase 1 — 분류 (Triage) — 코드 수정 금지

각 코멘트에 대해 아래를 판정한다. 결과는 테이블로 사용자에게 먼저 보고하고 승인 대기한다.

Read the full file on GitHub · 429 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. 11d ago First seen · 429 lines · 17 tokens per session scan A 7e90848c1a5b

Subscribe to this mod's changes

pr-review-check is a command published in the GitHub repository jhlee0409/claude-code-history-viewer (2,155 stars, last pushed 6d ago), licensed MIT. It adds 17 tokens to every session and 6,071 once invoked, about $0.0001 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 2026-08-30.