A command for reviewing a pull request, which is a proposed set of code changes for merging into a project. It supports GitHub, Bitbucket, or local branches, with either one reviewer or a three-person review panel.

Use it to review a GitHub or Bitbucket pull request, or compare a local branch with a base branch, optionally using a review council.

It organizes the checks needed before merging code and reports a review decision with severity counts and a report path. It also verifies the required provider access or local branches first.

review-pr — Command for Claude Code by mumerfarooq-con

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/mumerfarooq-con/asdlc-tools

Made for: Claude Code.

Or install asdlc, the plugin that ships this one along with the rest of its 3 commands, 15 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/mumerfarooq-con/asdlc-tools/review-pr.svg)](https://agentmods.dev/commands/mumerfarooq-con/asdlc-tools/review-pr)

Your own site

<a href="https://agentmods.dev/commands/mumerfarooq-con/asdlc-tools/review-pr"><img src="https://agentmods.dev/badge/commands/mumerfarooq-con/asdlc-tools/review-pr.svg" alt="Measured on agentmods" height="20"></a>

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 797 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.

Model	Per session	Once invoked
Fable 5.1	$0.00028	$0.00797
Opus 5	$0.00014	$0.00398
Sonnet 5	$0.00006	$0.00159
Haiku 4.5	$0.00003	$0.00080

Measured 8d ago against content hash f67533932628, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-pr 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.

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.

plugins/asdlc/commands/review-pr.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are coordinating a PR review for: $ARGUMENTS

Parse arguments:

A GitHub URL → GitHub mode. A Bitbucket URL → Bitbucket mode. A bare number → detect the provider from git remote get-url origin (github.com → GitHub mode, bitbucket.org → Bitbucket mode; ask the user if neither). A branch name → local mode (second token = base branch, defaulting to the repo's default branch).
--council present → Council mode (3 panelists + chair). Absent → Solo mode (single pr-reviewer).

Preflight

GitHub mode: confirm gh is authenticated (gh auth status). If not, tell the user to run gh auth login, and offer local mode.
Bitbucket mode: confirm the Atlassian/Bitbucket MCP server is connected. If not, tell the user to run /mcp, and offer local mode.
Local mode: git rev-parse --verify the branch and base; try origin/<branch> after a fetch if missing; ask the user if still missing.

Solo mode (default — cheap, for routine PRs)

Invoke pr-reviewer with the PR id/URL and provider mode, or branch + base.
Relay verdict, severity counts, report path.
Continue to "Handle verdict".

Council mode (--council — for critical / high-risk PRs)

Invoke these THREE panelists IN PARALLEL, each with the same PR id/URL and provider mode, or branch + base:
- pr-reviewer-security
- pr-reviewer-architecture
- pr-reviewer-correctness Each writes its own lens report to ./plans/pr-review-<id-or-slug>.<lens>.md. Do not review code yourself.
After all three return, invoke pr-review-chair with the same id/slug. The chair reads the three reports, reconciles them, and writes the canonical ./plans/pr-review-<id-or-slug>.md.
Relay the chair's authoritative verdict, must-fix count, canonical report path, top 3 must-fixes.
Continue to "Handle verdict" using the CHAIR's verdict (panelist verdicts are inputs, not the decision).

Handle verdict

REQUEST_CHANGES: ask the user what to do —
- fix findings now via prd-executor (must-fixes first; in council mode re-run only the chair after fixes unless a fix changed scope enough to warrant re-running a panelist — max 2 cycles, then escalate), or
- post findings as comments on the PR (GitHub: gh pr comment; Bitbucket: MCP) — ONLY with explicit user approval, comment-posting only, never approve/decline/merge, or
- leave the report local.
APPROVE: list remaining MAJOR/MINOR notes. Offer (don't do) posting an approval summary.

Read the full file on GitHub · 43 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.

8d ago First seen · 43 lines · 28 tokens per session scan A f67533932628

Subscribe to this mod's changes

review-pr is a command published in the GitHub repository mumerfarooq-con/asdlc-tools (2 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 797 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 2026-08-31.

Claude Code Code review Git and workflow Multi-Agent ai-agents claude-code-plugin sdlc

release

Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.

avelikiy/great_cto · 34 tokens

save

Save current session. Writes a session log with what was done, decisions made, and what's pending. Optional: commit & push.

avelikiy/great_cto · 26 tokens

hypothesis

Run hypothesis-driven research with git branching and evidence gathering.

cerodb/think-tank · 10 tokens

ccr

CCR (Compressed Context with Retrieval) — recall the full original of context that greatcto compressed/filtered out, by its short id. The retrieval half of the compression layer.

avelikiy/great_cto · 36 tokens

close-review

Month-end close / GL compliance check — invokes accounting-reviewer to produce TM-accounting-{slug}.md with double-entry integrity, ASC 606 revenue-recognition, period-lock, and SOX ITGC gaps.

avelikiy/great_cto · 43 tokens

coding-audit

Medical-coding / revenue-cycle compliance audit. Invokes rcm-reviewer to assess autonomous ICD-10-CM / CPT / HCPCS coding for False Claims Act exposure (upcoding/unbundling), NCCI edits + MUEs, medical necessity (LCD/NCD), modifier discipline, HIPAA minimum-necessary — and force a certified-coder (CPC/CCS) sign-off.

avelikiy/great_cto · 81 tokens