pr-conflict-refresh

A process for finding open GitHub pull requests that conflict with the current main branch after several changes have been merged. A pull request is a proposed code change, and a conflicting one cannot be merged until its branch is updated.

In plain words
What is it for?
Use it after a batch of merges to find dirty or conflicting pull requests, contact the responsible developers, and check that refreshed changes are tested again.
Why use it?
It prevents older pull requests from remaining based on an outdated version of the project. It lists affected requests, identifies their assigned developers, asks them to merge main into their branches, and tracks retesting.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/loopdive/js2/pr-conflict-refresh
Any agent
npx skills add loopdive/js2 --skill pr-conflict-refresh
Clone the repo
git clone --depth 1 https://github.com/loopdive/js2

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,281 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00045 $0.01281
Opus 5 $0.00023 $0.00641
Sonnet 5 $0.00009 $0.00256
Haiku 4.5 $0.00005 $0.00128

Measured 2d ago against content hash 77119e7143eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-conflict-refresh 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 2d 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/skills/pr-conflict-refresh/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Conflict Refresh

After a merge wave lands multiple PRs to main, older open PRs that built against the pre-merge baseline will become DIRTY. This skill systematically identifies them, pings their assigned devs to refresh, and follows up.

When to use

  • Immediately after running /merge-wave or closing out a batch of PRs
  • When GitHub's mergeability cache has had time to recompute (wait ~30s after the last merge)
  • Before ending a session so conflicts are handled before the next tech lead picks up

Step 1: List all open PRs with their mergeable status

gh pr list --limit 30 --json number,title,headRefName,author,mergeable,mergeStateStatus --jq '.[] | "\(.number)\t\(.mergeStateStatus)\t\(.author.login)\t\(.title[:60])"'

Step 2: Filter DIRTY / CONFLICTING

gh pr list --limit 30 --json number,title,headRefName,author,mergeStateStatus \
  --jq '.[] | select(.mergeStateStatus=="DIRTY" or .mergeable=="CONFLICTING") | "\(.number) \(.headRefName) \(.author.login) \(.title[:60])"'

UNKNOWN status is normal right after a merge — wait another 30s and re-check.

Step 3: Determine each conflicting PR's assigned dev

The PR branch name is the strongest hint: issue-NNNN-<slug> or worktree-issue-NNNN-<slug> corresponds to dev-NNN in our team convention (the dev agent that was spawned for the issue). Cross-reference with:

  1. The PR author (gh pr view <N> --json author)
  2. The issue file frontmatter in plan/issues/
  3. Active tmux panes / team registry in plan/method/agent-sessions.md if present

Step 4: Verify the PR had a positive pre-merge delta

Before asking a dev to refresh, check whether the PR was actually worth saving:

run_id=$(gh pr view <N> --json statusCheckRollup --jq '.statusCheckRollup[] | select(.name=="merge shard reports") | .detailsUrl' | grep -oE 'runs/[0-9]+' | head -1 | cut -d/ -f2)
mkdir -p output/pr-<N>
gh run download $run_id -n test262-merged-report -D output/pr-<N> 2>/dev/null
python3 -c "import json; d=json.load(open('output/pr-<N>/test262-report-merged.json')); s=d['summary']; print('pre-merge pass=', s['pass'])"

Read the full file on GitHub · 112 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. 2d ago First seen · 112 lines · 45 tokens per session scan A 77119e7143eb

Subscribe to this mod's changes

pr-conflict-refresh is a skill published in the GitHub repository loopdive/js2 (59 stars, last pushed 2d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,281 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 2026-08-30.