What is ticket-fleet?

A skill for solving multiple well-defined GitHub tickets in parallel, with each ticket handled in its own isolated copy of the code repository. It creates pull requests and coordinates reviews, interruptions, resumptions, merges, and conflicts.

Assigning batches of GitHub issues to separate coding sessions, reviewing their changes, resuming interrupted work, and merging completed pull requests.

It removes much of the manual coordination needed when several independent tickets must be implemented and reviewed at once.

ticket-fleet — Skill for Claude Code and Codex by Magnus-Gille

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.

Any agent

npx skills add Magnus-Gille/claude-skills --skill ticket-fleet

Clone the repo

git clone --depth 1 https://github.com/Magnus-Gille/claude-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/magnus-gille/claude-skills/ticket-fleet/github.svg)](https://agentmods.dev/skills/magnus-gille/claude-skills/ticket-fleet)

Your own site

<a href="https://agentmods.dev/skills/magnus-gille/claude-skills/ticket-fleet"><img src="https://agentmods.dev/badge/skills/magnus-gille/claude-skills/ticket-fleet/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/magnus-gille/claude-skills/ticket-fleet"><img src="https://agentmods.dev/badge/skills/magnus-gille/claude-skills/ticket-fleet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,775 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00073	$0.01775
Opus 5	$0.00036	$0.00888
Sonnet 5	$0.00015	$0.00355
Haiku 4.5	$0.00007	$0.00178

Measured 12d ago against content hash 00277d8c9235, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ticket-fleet scanned grade A with 1 finding 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 12d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/continue-ticket-broker.sh, scripts/continue-ticket-m5.sh, scripts/continue-ticket.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

plus optional per-ticket extra tools as trailing args (e.g. `"Bash(curl:*)"` for live-seam

ticket-fleet/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ticket-fleet — Headless Ticket Fleet

Resolve N well-scoped GitHub tickets in parallel: each ticket gets its own headless claude -p session in an isolated git worktree of the owning repo (so the repo's CLAUDE.md governs it), produces a PR, self-runs a Codex review, and reports uncertainties. The orchestrator (you, the main session) does a second review leg per PR, relays uncertainties to the user, and handles merges + conflicts.

Proven: 2026-07-03→04, 23 tickets across 10 repos, 29 PRs merged, 0 rejected; cross-model review caught 2 criticals + 1 high the authoring model missed; survived a mid-flight spend-limit outage via --continue resume.

Usage

/ticket-fleet <ticket-list> — e.g. verdandi#9 skuld#3 heimdall#104 or "all open from:grimnir tickets"

Assets

scripts/run-ticket.sh <repo_dir> <issue_no> <model> <prompt_file> <log_file> — creates worktree ~/repos/.wt/<repo>-t<issue> on branch ticket/<issue>-headless from origin/<default>, runs the headless session with the gated allowlist, logs everything.
scripts/continue-ticket.sh <worktree_dir> <model> <log_file> — resumes an interrupted session in its worktree via claude -p --continue (conversation context + partial edits survive).
scripts/run-ticket-m5.sh / scripts/continue-ticket-m5.sh — M5-enabled variants (proven 2026-07-04, 4/4 tickets): add mcp__m5__ask/mcp__m5__list_models to the allowlist plus optional per-ticket extra tools as trailing args (e.g. "Bash(curl:*)" for live-seam tickets). Use these when sessions should offload bounded sub-tasks to the M5 box; include an M5-offload paragraph in the prompt's EXTRA section requiring the session to VERIFY every M5 output before use, and add an M5: line to the FINAL REPORT format. Reliability data so far (2026-07-04): qwen3-coder review legs were clean and correct on 3 TypeScript diffs but confabulated 5-of-6 findings on a shell/docs diff — trust the M5 review leg on TS, treat its shell/docs findings as hypotheses to verify, and always verify its codegen with tests.
templates/ticket-prompt.md — the per-ticket prompt. Fill {ISSUE}, {TITLE}, {EXTRA_TASK_SPECIFIC_GUIDANCE} (2–6 sentences: concrete scope, files, constraints, known traps). The EXTRA section is where quality is won — be specific per ticket.

Read the full file on GitHub · 109 lines

Files

What ships with it

7 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.

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.

12d ago First seen · 109 lines · 73 tokens per session scan A 00277d8c9235

Subscribe to this mod's changes

ticket-fleet is a skill published in the GitHub repository Magnus-Gille/claude-skills (5 stars, last pushed 6d ago), licensed MIT. It adds 73 tokens to every session and 1,775 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Git and workflow Project management

mcore-split-pr

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

NVIDIA/skills · 25 tokens

shiplog

Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.

aeonfun/aeon · 46 tokens

llxprt-issue-workflow

Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the stepfun-37 smoke test), open code review (ocr), PR…

vybestack/llxprt-code · 87 tokens

ticket-fleet