harness:pr-fleet

harness:pr-fleet is a command for Claude Code from Intense-Visions/harness-engineering. It costs 78 tokens per session (575 once invoked), scanned A, original, MIT.

An orchestrator for processing a queue of open pull requests. It coordinates isolated review helpers, verifies continuous-integration checks and review results across operating systems, and merges only the changes a person approved.

In plain words
What is it for?
Use it to triage pull requests, run isolated review and repair work, verify readiness, merge approved changes, and close superseded requests.
Why use it?
It reduces manual work across many pull requests while keeping approval, independent verification, and branch-protection rules in control of merging.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Part of the harness-claude plugin — 85 skills, 89 commands, 16 agents, 4 hooks, 4 MCP servers shipped together

Good fit Use it to triage pull requests, run isolated review and repair work, verify readiness, merge approved changes, and close superseded requests.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/intense-visions/harness-engineering/pr-fleet
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.

Clone the repo
git clone --depth 1 https://github.com/Intense-Visions/harness-engineering

Made for: Claude Code.

Or install harness-claude, the plugin that ships this one along with the rest of its 85 skills, 89 commands, 16 agents, 4 hooks, 4 MCP servers.

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 harness:pr-fleet

README.md
[![agentmods](https://agentmods.dev/badge/commands/intense-visions/harness-engineering/pr-fleet.svg)](https://agentmods.dev/commands/intense-visions/harness-engineering/pr-fleet)
Your own site
<a href="https://agentmods.dev/commands/intense-visions/harness-engineering/pr-fleet"><img src="https://agentmods.dev/badge/commands/intense-visions/harness-engineering/pr-fleet.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 575 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.
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 $0.00078 $0.00575
Opus 5 $0.00039 $0.00287
Sonnet 5 $0.00016 $0.00115
Haiku 4.5 $0.00008 $0.00057

Measured 4d ago against content hash 617246c9fbf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

harness: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 4d 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-plugin/commands/pr-fleet.md · 41 lines

What it actually says

Phases:

  • select: Enumerate the open-PR queue, triage each PR into the land-readiness taxonomy, cross-check for superseded/already-resolved PRs, and order landable candidates by land-priority
  • confirm: Present the triaged queue in one round — superseded items flagged for closure, decision forks as questions, proposed concurrency — for a single up-front human approval that carries the per-PR merge authorization
  • dispatch: Fan out worktree-isolated subagents that each run the real code-review pipeline for one PR, push fix commits for mechanical findings, and re-run CI — never merging, never fabricating approval — capped at the concurrency governor
  • verify: Independently confirm each PR proposed to land is CI-green across all target operating systems plus the project's required checks, carries a review verdict, and is mergeable — never by subagent self-report
  • land: Merge only the PRs that are both human-approved in confirm and independently verified, honoring branch protection; emit a one-row-per-PR batch summary and close superseded PRs citing the superseding PR; never merge unapproved or unverified work

<execution_context> @agents/skills/claude-code/pr-fleet/SKILL.md @agents/skills/claude-code/pr-fleet/skill.yaml </execution_context>

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. 4d ago First seen · 41 lines · 78 tokens per session scan A 617246c9fbf9

Subscribe to this mod's changes

harness:pr-fleet is a command published in the GitHub repository Intense-Visions/harness-engineering (20 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 575 once invoked, about $0.0004 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 2026-09-03.