A pull-request merging workflow for GitHub. A pull request is a proposed set of code changes waiting to be added to a shared codebase.

Use it to merge or squash-merge pull requests, inspect the current pull request, check CI results, and clean up the source branch where possible.

It checks whether automated tests and other checks have passed before merging, then reports what happened to the original source branch.

merge — Skill for Claude Code by feniix

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 feniix/pi-extensions --skill merge

Clone the repo

git clone --depth 1 https://github.com/feniix/pi-extensions

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/feniix/pi-extensions/merge/github.svg)](https://agentmods.dev/skills/feniix/pi-extensions/merge)

Your own site

<a href="https://agentmods.dev/skills/feniix/pi-extensions/merge"><img src="https://agentmods.dev/badge/skills/feniix/pi-extensions/merge/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/feniix/pi-extensions/merge"><img src="https://agentmods.dev/badge/skills/feniix/pi-extensions/merge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,055 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Anti-Refusal · line 34
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.

How audits are shown

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	$0.00052	$0.01055
Opus 5	$0.00026	$0.00528
Sonnet 5	$0.00010	$0.00211
Haiku 4.5	$0.00005	$0.00105

Measured 9d ago against content hash f8ad743b2be3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

merge 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 9d 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.

packages/pi-devtools/skills/merge/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Merge PR Workflow

Merge or squash-merge a pull request and optionally request best-effort source-branch cleanup.

Tool Restrictions (Critical)

Use ONLY these tools:

devtools_check_ci - Check CI status before merging
devtools_merge_pr - Standard merge (merge commit)
devtools_squash_merge_pr - Squash merge
devtools_get_repo_info - Get current PR info

Process

Step 1: Identify the PR

If user provides PR number, use it. Otherwise:

Call devtools_get_repo_info to get current branch
Find PR for current branch via gh pr list

Step 2: Check CI Status

Important: Always check CI before merging.

Call devtools_check_ci:

If checks are failing or pending: warn the user and ask whether to proceed or wait
If checks are passing: continue
If no CI checks exist for the PR: continue without warning or additional confirmation

Step 3: Merge PR

Ask user for merge strategy:

Merge commit (devtools_merge_pr): Preserves all commit history
Squash merge (devtools_squash_merge_pr): Combines all commits into one

Default: Squash merge (cleaner history).

Call the appropriate tool with:

prNumber: The PR number (or detect from current branch)
deleteBranch: true to request best-effort remote and local cleanup
squash: true for squash merge

Step 4: Report Merge and Cleanup

Branch first on mergeStatus before interpreting any cleanup fields:

When mergeStatus is pending, the merge is queued or auto-merge is pending. Explicitly report that it is pending and that cleanup was skipped; do not report the PR as merged or describe cleanup as incomplete after a successful merge.
When mergeStatus is unknown, the merge command was accepted but its result could not be confirmed. Report the uncertainty and skipped cleanup, and do not retry the merge automatically.
Only when mergeStatus is merged, report the successful merge and then inspect remoteCleanup and localCleanup separately. remoteCleanup reports whether the remote head ref was deleted, skipped, or failed. localCleanup reports whether the local branch was deleted, retained by one or more worktrees, skipped, or failed. When it is retained, report each retaining worktree path and state. Use cleanupComplete to summarize whether all requested cleanup completed.

Read the full file on GitHub · 106 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.

9d ago First seen · 106 lines · 52 tokens per session scan A f8ad743b2be3

Subscribe to this mod's changes

merge is a skill published in the GitHub repository feniix/pi-extensions (23 stars, last pushed 5d ago), licensed MIT. It adds 52 tokens to every session and 1,055 once invoked, about $0.0003 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.

Git and workflow TypeScript ai-agents coding-agents developer-tools mcp pi

pi-package-sandbox-test

Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.

spences10/my-pi · 40 tokens

agentplane-release-and-packaging-operator

Use when preparing, validating, publishing, auditing, or recovering an Agentplane release, especially package build ordering, version parity, npm/GitHub/GHCR/external distribution publication, public install smoke tests, hosted publish evidence, or release CI failures.

basilisk-labs/agentplane · 60 tokens

merge