Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ao92265/claude-code-playbooknpx agentmods add skills/ao92265/claude-code-playbook/pr-fleetWrote 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/ao92265/claude-code-playbook/pr-fleet)<a href="https://agentmods.dev/skills/ao92265/claude-code-playbook/pr-fleet"><img src="https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/pr-fleet.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00117 | $0.02208 |
| Opus 5 | $0.00059 | $0.01104 |
| Sonnet 5 | $0.00023 | $0.00442 |
| Haiku 4.5 | $0.00012 | $0.00221 |
Grade A, and why
pr-fleet 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 7d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Fleet — Parallel PR Orchestrator
Replaces sequential ralph-loop merges with concurrent subagent workers. One coordinator + N parallel workers per PR via git worktrees. Runs in two modes (see below).
When to invoke
- Batch clearing of PR backlog, overnight or interactive
- Schedulable via cron through
claude -p "/pr-fleet"headless mode (autonomous mode only) - Repo has open PR queue (>3 PRs makes parallelism worthwhile)
Modes
- Autonomous (default). Unattended overnight run. Dispatches the whole queue (chunked to the 20-PR cap), never merges, writes a morning report for the human to action. No pauses.
- Interactive (
--interactive, or triggered by "merge queue" / "pr backlog" / "/pr-merge-queue"). Same triage + worker protocol, but processes in batches of 5 with a checkpoint after each batch: post a summary, pause for user confirmation, and only then merge the confirmed PRs. Use this when the user wants to stay in the loop rather than wake up to a fait accompli. See Step 3a.
Shared State
.omc/state/pr-swarm.json (per-repo) tracks every PR in the run:
{ "prs": { "8669": { "status": "in_progress", "claimed_by": "worker-2", "attempts": 1, "blocker_reason": null } } }
Statuses: pending | in_progress | done | blocked. Atomic claim/release via state-helpers.sh (mkdir-mutex lock). Workers MUST claim before acting; if claim returns non-zero, skip to next PR.
Coordinator Protocol
Step 0 — Pre-flight (REQUIRED)
Run bash ~/.claude/skills/pr-fleet/state-helpers.sh preflight. Hard-fails on missing gh/jq, unauthenticated gh, or git fetch failure.
Additionally:
- If any queued PR touches
prisma/**or.github/workflows/**, setOMC_SKIP_HOOKS=protect-pathsfor the run AND surface to user before dispatch. - Verify
git push --dry-run --force-with-leaseagainst an arbitrary head returns no firewall block.
If pre-flight fails: STOP. Do not dispatch — workers will all stall on the same blocker.
Step 1 — Triage
What ships with it
1 file 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.
- 7d ago First seen · 166 lines · 0 tokens per session scan A b2cc4a3ef796
pr-fleet is a skill published in the GitHub repository ao92265/claude-code-playbook (10 stars, last pushed 20d ago), licensed MIT. It adds 117 tokens to every session and 2,208 once invoked, about $0.0006 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.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
write-pr
Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.