parallel-pr-scope-overlap-tiebreaker-delta-check

parallel-pr-scope-overlap-tiebreaker-delta-check is a skill for Claude Code from wan-huiyan/agent-traffic-control. It costs 384 tokens per session (3,607 once invoked), scanned A, original, MIT.

A review method for choosing between two pull requests that implement the same change, where a pull request is a proposed code change for review and merging.

In plain words
What is it for?
Use it to compare both pull-request diffs and check for meaningful differences before closing one and merging the other.
Why use it?
It prevents simple tie-breakers such as age, merge status, or reviewer approval from selecting the weaker implementation.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions Claude Code.

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

Good fit Use it to compare both pull-request diffs and check for meaningful differences before closing one and merging the other.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wan-huiyan/agent-traffic-control/parallel-pr-scope-overlap-tiebreaker-delta-check
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 parallel-pr-scope-overlap-tiebreaker-delta-check
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 parallel-pr-scope-overlap-tiebreaker-delta-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/parallel-pr-scope-overlap-tiebreaker-delta-check/github.svg)](https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/parallel-pr-scope-overlap-tiebreaker-delta-check)
Your own site
<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/parallel-pr-scope-overlap-tiebreaker-delta-check"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/parallel-pr-scope-overlap-tiebreaker-delta-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 parallel-pr-scope-overlap-tiebreaker-delta-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/parallel-pr-scope-overlap-tiebreaker-delta-check"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/parallel-pr-scope-overlap-tiebreaker-delta-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 384 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,607 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 $0.00384 $0.03607
Opus 5 $0.00192 $0.01803
Sonnet 5 $0.00077 $0.00721
Haiku 4.5 $0.00038 $0.00361

Measured 11d ago against content hash 03acd60927d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

parallel-pr-scope-overlap-tiebreaker-delta-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.

plugins/agent-traffic-control/skills/parallel-pr-scope-overlap-tiebreaker-delta-check/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-Tiebreaker Delta Check on Scope-Overlapping Parallel PRs

Problem

Two parallel sessions independently opened PRs targeting the same issue (same fix scope, same files, same goal). A session-handoff prompt later asks a third session to pick a winner. The prompt's recommended tiebreaker is some combination of:

  • "Merge the first-mover" (older PR by createdAt)
  • "Merge the one that's clean against main" (mergeable: CLEAN, no rebase needed)
  • "Merge the one with reviewer APPROVE" (assumed implies higher quality)
  • "Merge the one with wider scope" (e.g., bundles verification + handoff doc)

These rules are about merge mechanics, not implementation quality. They can — and do — ship the inferior PR while the better implementation gets closed.

Trigger Conditions

ALL of the following must hold:

  1. Two parallel PRs are open simultaneously, targeting overlapping scope (same issue number cited as Closes #N; same files touched; same fix intent).
  2. A session-handoff prompt explicitly suggests a tiebreaker default ("merge #X because it's first-mover", "clean against main", "wider scope"), or you're operating from such instructions in auto-mode.
  3. The two PRs were authored by different sessions (different worktrees, different branches, different timestamps, different commit authors or different co-authored-by chains).
  4. You haven't yet run gh pr diff <A> and gh pr diff <B> side-by-side to compare implementations.

If those conditions hold and you're about to merge based on the prompt's recommendation alone, STOP — run the delta check first.

Solution

Step 1 — Refresh both PR snapshots

A prompt authored hours ago may cite stale state (e.g., "PR #X is CLEAN, PR #Y is CONFLICTING"). Main may have advanced; the relative state often flips by the time the next session runs.

gh pr view <A> --json state,mergeable,mergeStateStatus,statusCheckRollup,additions,deletions,createdAt,headRefName
gh pr view <B> --json state,mergeable,mergeStateStatus,statusCheckRollup,additions,deletions,createdAt,headRefName

Read the full file on GitHub · 285 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 · 285 lines · 384 tokens per session scan A 03acd60927d3

Subscribe to this mod's changes

parallel-pr-scope-overlap-tiebreaker-delta-check is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed 6d ago), licensed MIT. It adds 384 tokens to every session and 3,607 once invoked, about $0.0019 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

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