logistics: Skill for Claude Code

.claude/skills/ship-pr-queue/SKILL.md

ship-pr-queue is a skill for Claude Code from Indemnity83/logistics. It costs 104 tokens per session (2,511 once invoked), scanned A, original, MIT.

A workflow for processing every open pull request aimed at an `mc/` branch. It handles checks and review fixes, then merges and ports eligible changes to other version branches.

In plain words
What is it for?
Use it to clear an open pull-request queue, fix non-mergeable requests, and ship mergeable ones.
Why use it?
It prevents the release queue from being handled inconsistently or with unnecessary pushes.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; positional $N argument.

This is Indemnity83/logistics's own configuration. It tells Claude Code how to work on logistics itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything logistics configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Indemnity83/logistics. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Indemnity83/logistics/mc/26.2/.claude/skills/ship-pr-queue/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Indemnity83/logistics

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.

agentmods badge for ship-pr-queue

README.md
[![agentmods](https://agentmods.dev/badge/skills/indemnity83/logistics/ship-pr-queue.svg)](https://agentmods.dev/skills/indemnity83/logistics/ship-pr-queue)
Your own site
<a href="https://agentmods.dev/skills/indemnity83/logistics/ship-pr-queue"><img src="https://agentmods.dev/badge/skills/indemnity83/logistics/ship-pr-queue.svg" alt="Measured on agentmods" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,511 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 Memory Poisoning · line 226
    Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
    Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00104 $0.02511
Opus 5 $0.00052 $0.01256
Sonnet 5 $0.00021 $0.00502
Haiku 4.5 $0.00010 $0.00251

Measured 3d ago against content hash a3b7aa2a8ac9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ship-pr-queue 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 3d 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/ship-pr-queue/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship the PR queue

One pass = one PR taken as far as it can go. Repeat until the queue is empty. Do not batch operations across PRs: every push re-triggers a review that costs roughly $1, so wasted pushes are wasted budget.

Build the queue

gh pr list --state open --limit 100 \
  --json number,title,baseRefName,headRefName,isDraft,labels,mergeStateStatus \
  --jq '.[] | select(.baseRefName|startswith("mc/"))
            | select(.headRefName|startswith("release-please")|not)
            | select([.labels[].name]|index("autorelease: pending")|not)
            | select(.isDraft|not)
            | "#\(.number)\t\(.mergeStateStatus)\t\(.baseRefName)\t\(.title)"'

Release-please PRs are excluded on both signals (head branch and label) because they are merged deliberately as part of the release cycle, not by this loop.

UNKNOWN is not a state — it means GitHub has not computed mergeability yet. Asking is what triggers the computation, so the first query after a base moves usually returns UNKNOWN for most of the queue. Run the query again a few seconds later and it resolves. Never classify a PR off an UNKNOWN; you would treat a clean PR as broken and "fix" a problem that does not exist.

Report the queue to the user before acting, then take PRs in order, CLEAN ones first — shipping those shrinks the queue fastest and moves the base for the rest.

Classify

mergeStateStatus is the primary signal:

Status Meaning Branch
CLEAN green and no blockers Ship
BLOCKED a required check is pending/failing, or a review thread is unresolved Diagnose first (below)
DIRTY merge conflict with base Fix (merge base in)
BEHIND base moved gh pr update-branch <n>
UNSTABLE non-required check failing judge: usually Fix

BLOCKED does not imply broken. A required check that is still pending blocks the PR exactly like a failing one, and a review takes ~2 minutes. Before changing anything, separate the three causes:

Read the full file on GitHub · 227 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. 3d ago First seen · 227 lines · 104 tokens per session scan A a3b7aa2a8ac9

Subscribe to this mod's changes

ship-pr-queue is a skill published in the GitHub repository Indemnity83/logistics (6 stars, last pushed 2d ago), licensed MIT. It adds 104 tokens to every session and 2,511 once invoked, about $0.0005 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 2026-09-04.

Related

Other skills, from other repositories

github-automation

GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.

ruvnet/ruflo · 61 tokens

github

GitHub via gh CLI: PRs, issues, reviews, repos, auth.

NousResearch/hermes-agent · 19 tokens

github

Full GitHub CLI control — issues, PRs, code reviews, repo management. Uses gh CLI with auth detection, rate limiting, and templates. Triggers on: github, issue, pull request, PR, code review, repo, branch, label, assignee, milestone, release, workflow, actions.

adolfousier/opencrabs · 0 tokens

pre-publish-review

Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…

code-yeongyu/oh-my-openagent · 161 tokens

parallel-pr-review

Use when asked to "review the open PRs", review a batch or stack of pull requests, or run a recurring PR-review pass on a repo — especially with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.

suyoumo/ClawProBench · 67 tokens

no-mistakes

Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.

stevesolun/ctx · 67 tokens