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.
npx skills add Mathews-Tom/armory --skill pr-swarmgit clone --depth 1 https://github.com/Mathews-Tom/armoryWrote 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.
[](https://agentmods.dev/skills/mathews-tom/armory/pr-swarm)<a href="https://agentmods.dev/skills/mathews-tom/armory/pr-swarm"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/pr-swarm/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.
<a href="https://agentmods.dev/skills/mathews-tom/armory/pr-swarm"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/pr-swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00171 | $0.03029 |
| Opus 5 | $0.00086 | $0.01515 |
| Sonnet 5 | $0.00034 | $0.00606 |
| Haiku 4.5 | $0.00017 | $0.00303 |
Grade A, and why
pr-swarm 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.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Swarm — Parallel Own-PR-to-Green Loops
Problem
A repository checkout can only have one branch active at a time. A user with N independent, already-open pull requests — disjoint branches, disjoint changed files, no real relationship between them — that each need conflict resolution, review-feedback triage, and CI watching wastes wall-clock time driving them one after another when nothing about them actually depends on each other.
Root cause
git worktree removes the one-checkout constraint: N branches can be checked out simultaneously, each in its own directory, sharing one .git object store. Combined with N independent headless Claude Code sessions (own process, own context window, own token budget — not subagents sharing this session's budget), the PRs can be driven to green concurrently with zero cross-talk.
Reference Files
| File | Contents | Load When |
|---|---|---|
references/launch-mechanics.md |
claude -p flags, detached background launch pattern, watchdog/liveness checks, exit-code capture |
Phase 5 (Launch) |
references/verification-gates.md |
GitHub API correctness pitfalls: stale mergeStateStatus, body-only bot reviews, stale statusCheckRollup entries, review-thread pagination, reacting to the first failing check instead of waiting for the full CI matrix |
Phase 6 (Monitor & Verify) |
references/lane-prompt-template.md |
The literal per-lane task prompt (termination conditions, orientation, conflict resolution, watch loop) | Phase 4 (Lane Prompt) |
Scope boundary
This skill drives PRs that are already open. It does not create PRs from issues, does not decide whether unrelated PRs are safe to parallelize (that's Phase 2, and it's a hard stop on any real overlap, not a judgment call this skill makes silently), and does not resolve PRs closed by a maintainer for policy reasons — see "Mid-loop external closure" in Phase 6.
Workflow
Phase 1 — Resolve each PR
For every requested PR number N:
gh pr view N --json number,state,headRefName,baseRefName,author,url,isCrossRepository
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 181 lines · 171 tokens per session scan A 997c5960909a
pr-swarm is a skill published in the GitHub repository Mathews-Tom/armory (316 stars, last pushed yesterday), licensed MIT. It adds 171 tokens to every session and 3,029 once invoked, about $0.0009 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.
Other skills, from other repositories
gh-issues
Use when creating, searching, updating, or managing GitHub issues via CLI. Triggers: "issue", "create issue", "gh issue", "task tracking", "context", "handoff", "resume task", "session context", "save progress", "active tasks", "in-progress", "my tasks", "open issues". Covers: gh commands, bulk operations, JSON/jq…
mx-pr
Draft a pull request from the feature spec and git log, run an autonomous commit-history cleanup (content check), then publish to GitHub or GitLab (Bitbucket experimental) — or hand off. Use when a feature branch is ready for PR, standalone or from mx-flow. Usage: /mx-pr [name].
mx-commit
Commit all pending changes as one commit per logical concern, following the project's message convention (type prefix, 50-char subject, English). Use when the working tree may hold several changes or the convention must be enforced; a single trivial change can use plain git commit. Usage: /mx-commit [--auto].
safe-public-release
Use when publishing, open-sourcing, exporting, sanitizing, or moving code, agent skills, prompts, templates, fixtures, datasets, workshop assets, or other artifacts from a private repository, vendor/runtime environment, or mixed working directory into a public repository or registry. Builds a provenance inventory…
dirty-worktree-discipline
Keeps agent work safe in messy repositories. Use when git status is dirty, unrelated files exist, generated artefacts are present, multiple agents share a repo, or you must commit only the intended slice without damaging someone else's work.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.