squad-fleet

squad-fleet is a skill for Claude Code, Codex from sabbour/agentweaver. It costs 192 tokens per session (2,154 once invoked), scanned A, original, MIT.

A parallel GitHub-issue work system that gives each issue its own branch and worktree, which is a separate checkout of the repository.

In plain words
What is it for?
Use it to select prioritized open GitHub issues, assign them to separate agents, and run their implementation work in isolated worktrees.
Why use it?
It lets several agents work at the same time while reducing file conflicts between their changes. It also sorts issues and skips work already being handled.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/sabbour/agentweaver/squad-fleet
Any agent
npx skills add sabbour/agentweaver --skill squad-fleet
Clone the repo
git clone --depth 1 https://github.com/sabbour/agentweaver

Made for: Claude Code, Codex.

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 squad-fleet

README.md
[![agentmods](https://agentmods.dev/badge/skills/sabbour/agentweaver/squad-fleet.svg)](https://agentmods.dev/skills/sabbour/agentweaver/squad-fleet)
Your own site
<a href="https://agentmods.dev/skills/sabbour/agentweaver/squad-fleet"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/squad-fleet.svg" alt="Measured on agentmods" height="20"></a>
Per session 192 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,154 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00192 $0.02154
Opus 5 $0.00096 $0.01077
Sonnet 5 $0.00038 $0.00431
Haiku 4.5 $0.00019 $0.00215

Measured 5d ago against content hash d56f29c64092, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

squad-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 5d 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.

.copilot/skills/squad-fleet/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Squad Fleet — Parallel Issue Execution

Fleet mode is how Squad maximizes throughput: instead of working issues one by one, multiple agents run simultaneously in isolated git worktrees. Each agent owns one issue, one branch, one PR. They can't conflict with each other because they're in separate checkouts.

Step 1 — Show the current board

Before doing anything, print a status snapshot so Ahmed can see where things stand. Run the issue-status skill (.copilot/skills/agentweaver-issue-status/SKILL.md) or call:

gh issue list --state open --label "go:yes" \
  --json number,title,labels,state --limit 30

Display as a summary table: # | Title | Squad | Priority | Type.

Step 2 — Build the work queue

Fetch all open issues labeled go:yes. Sort them in this priority order:

  1. priority:p0 bugs first (blocking / production outage)
  2. priority:p1 bugs
  3. priority:p0 / priority:p1 chores
  4. priority:p2 bugs
  5. Features and remaining chores
  6. Spikes last

Within each tier, sort by issue number ascending (older issues first).

Skip issues that already have an open PR (gh pr list --search "#{N}") or an active worktree (git worktree list).

Step 3 — Conflict analysis

Before spawning, check whether any queued issues would touch overlapping files. Two issues conflict when their domains have shared file ownership:

If both issues touch... They conflict
Same component file (apps/web/src/...) Yes
Same API controller/service Yes
Same k8s manifest Yes
Different domains entirely (e.g. frontend + infra) No

How to check: Read the issue title and labels. Use the routing table in .squad/routing.md to determine the domain files each issue would touch. If two issues both route to squad:trinity AND likely edit the same component, serialize them (add to "stacked" queue). If they route to different squad members, they're safe to parallelize.

Group the queue into parallel batches:

  • Batch 1: all conflict-safe issues (run simultaneously)
  • Batch 2+: dependent or conflicting issues (run after batch 1 merges)

Read the full file on GitHub · 229 lines

Files

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.

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. 5d ago First seen · 229 lines · 192 tokens per session scan A d56f29c64092

Subscribe to this mod's changes

squad-fleet is a skill published in the GitHub repository sabbour/agentweaver (5 stars, last pushed today), licensed MIT. It adds 192 tokens to every session and 2,154 once invoked, about $0.0010 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.

Related

Other skills, from other repositories