stacked-pr-review-per-base-diff-and-attach

stacked-pr-review-per-base-diff-and-attach is a skill for Claude Code from wan-huiyan/agent-traffic-control. It costs 43 tokens per session (2,492 once invoked), scanned A, original, MIT.

A review procedure for a stack of dependent pull requests, where each later branch includes the earlier one. It compares every pull request with its own base branch and stores the review reports on the bottom branch.

In plain words
What is it for?
Use it to review stacked pull requests, produce separate correctness, architecture, and security reports, and attach those reports without polluting the stack's top branch.
Why use it?
It prevents reviewers from blaming a later pull request for changes that belong to earlier ones. It also keeps review reports from appearing as changes introduced by the top pull request.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions Claude Code.

Part of the agent-traffic-control plugin — 105 skills shipped together

Good fit Use it to review stacked pull requests, produce separate correctness, architecture, and security reports, and attach those reports without polluting the stack's top branch.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wan-huiyan/agent-traffic-control/stacked-pr-review-per-base-diff-and-attach
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 wan-huiyan/agent-traffic-control --skill stacked-pr-review-per-base-diff-and-attach
Clone the repo
git clone --depth 1 https://github.com/wan-huiyan/agent-traffic-control

Made for: Claude Code.

Or install agent-traffic-control, the plugin that ships this one along with the rest of its 105 skills.

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 stacked-pr-review-per-base-diff-and-attach

README.md
[![agentmods](https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/stacked-pr-review-per-base-diff-and-attach/github.svg)](https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/stacked-pr-review-per-base-diff-and-attach)
Your own site
<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/stacked-pr-review-per-base-diff-and-attach"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/stacked-pr-review-per-base-diff-and-attach/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 stacked-pr-review-per-base-diff-and-attach

Your own site · 80×15
<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/stacked-pr-review-per-base-diff-and-attach"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/stacked-pr-review-per-base-diff-and-attach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,492 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 $0.00043 $0.02492
Opus 5 $0.00022 $0.01246
Sonnet 5 $0.00009 $0.00498
Haiku 4.5 $0.00004 $0.00249

Measured 6d ago against content hash abc74f3932a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

stacked-pr-review-per-base-diff-and-attach 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 6d 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/agent-traffic-control/skills/stacked-pr-review-per-base-diff-and-attach/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stacked PR review: per-base diffs + base-branch attachment

Problem

Reviewing a stack of N dependent PRs (where #B is based on #A, #C is based on #B, etc., rather than each PR being based on main) hits two distinct issues:

  1. Diff capture for reviewer agents. If you naively run gh pr diff <N> against every PR in the stack, gh defaults to comparing against the PR's declared base — which is correct. But if you pre-filter via git diff main..pr-branch, you'll include all upstream PRs' changes in the "downstream PR's diff," and reviewers will flag findings against code that actually shipped 2 PRs ago. The reviewer attributes the finding to the wrong PR, and the author of the downstream PR is left confused.

  2. Where to commit the review reports. Once 3 reviewer agents have produced reviewer_correctness.md, reviewer_architecture.md, reviewer_security.md, they need to live somewhere reachable by every PR in the stack — but committing them to the top-of-stack PR pollutes that PR's diff (the reports become "changes" the topmost PR is making). The base-of-stack PR is the natural home.

Context / Trigger Conditions

  • A stack of 2+ open PRs exists where the head PR's base is another open PR (not main)
  • You're dispatching a multi-agent review panel (e.g., roundtable:agent-review-panel) to cover the whole stack
  • One of these symptoms:
    • Reviewer flags a "missing feature" in PR #C that was actually added in PR #A
    • Reviewer's diff snapshot shows ~3× as many lines as the PR's actual change
    • You want PR #A's reviewer to see the docs/reviews/ folder but committing it to PR #C's branch means PR #A can't see it
    • The orchestrator wonders "which branch do I commit this report to?"

Solution

Pattern 1: per-PR base-aware diff capture

For each PR in the stack, capture its diff against ITS OWN base, not against main:

mkdir -p /tmp/stack-review
for pr in 57 58 59; do
  # gh pr diff defaults to PR's declared base (the right thing)
  gh pr diff $pr -R <org>/agentic-ai-workshop \
    > /tmp/stack-review/pr${pr}-vs-its-base.diff
  # Also save the body so reviewers have author intent
  gh pr view $pr -R <org>/agentic-ai-workshop --json body -q .body \
    > /tmp/stack-review/pr${pr}-body.md
done
wc -l /tmp/stack-review/*.diff

Read the full file on GitHub · 183 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. 6d ago First seen · 183 lines · 43 tokens per session scan A abc74f3932a2

Subscribe to this mod's changes

stacked-pr-review-per-base-diff-and-attach is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 2,492 once invoked, about $0.0002 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 2026-09-05.

Related

Other skills, from other repositories

pr-check

PR review compliance: fetch review comments from an open PR, categorize as resolved/unresolved/dismissed, critically evaluate fixable items, implement approved fixes, and reply inline. Pass --unattended to halt on human-judgment items (emitted as Pending-Human) instead of prompting via AskUserQuestion.

rube-de/cc-skills · 67 tokens

babysit

PR babysitter: monitors CI status, auto-rebases when behind, auto-fixes CI where possible, delegates review comment handling to dlc:pr-check, and re-requests review after fixes. Designed for /loop usage with Remote Control.

rube-de/cc-skills · 53 tokens

git-ops

Git hygiene: clean up merged branches, prune stale remotes, and verify repository state.

rube-de/cc-skills · 22 tokens

misuzu

Respond to PR review comments semi-automatically. Fetches all review threads and comments, splits them into logical units, fixes and commits one unit at a time, then replies and resolves review threads. Use when the user wants to address PR review feedback or respond to review comments.

ncaq/konoka · 59 tokens

pr-style

Pull request style guidelines covering title, body, assignee, and label selection. Use when writing or proposing GitHub pull requests, including direct gh pr create invocations outside the /pr skill.

ncaq/konoka · 44 tokens

swarm-pi-review

Review a Git working tree or branch with read-only Pi workers. Use standard for bugs, security, regressions, and missing tests; use lean for diff-bound simplification, deletion, reuse, YAGNI, or native replacements. Route one question to ask and broader risk analysis to orchestrate.

JiaWeiXie/swarm-pi-code-plugin · 66 tokens