What is ticket-start?

A setup tool for starting work on GitHub tickets in an isolated Git branch and worktree, a separate working directory connected to the same repository. It fetches the latest main branch and creates a separate local database for the ticket.

Use it to validate tickets, create isolated workspaces, prepare branches, and set up ticket-specific Beads databases before development.

It prevents ticket work from mixing with other changes and avoids starting from an outdated local branch.

How prebid/salesagent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to prebid/salesagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/prebid/salesagent/main/.claude/skills/ticket-start/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/prebid/salesagent

Made for: Claude Code.

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/prebid/salesagent/ticket-start.svg)](https://agentmods.dev/skills/prebid/salesagent/ticket-start)

Your own site

<a href="https://agentmods.dev/skills/prebid/salesagent/ticket-start"><img src="https://agentmods.dev/badge/skills/prebid/salesagent/ticket-start.svg" alt="Measured on agentmods" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 743 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.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.00743
Opus 5	$0.00030	$0.00371
Sonnet 5	$0.00012	$0.00149
Haiku 4.5	$0.00006	$0.00074

Measured 2d ago against content hash cdd534c5bbeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ticket-start 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (ticket-start.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.

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/skills/ticket-start/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ticket Start

Sets up the workspace for a ticket. Does no research and writes no code — that is /prime's job, and it runs in the new worktree where the context belongs.

Usage

.claude/skills/ticket-start/ticket-start.sh 1776
.claude/skills/ticket-start/ticket-start.sh 1776 1781      # a related batch

The first ticket names the branch and the worktree. Pass several only when they are genuinely one change — otherwise start them separately so each gets its own PR.

What it does

Validates every ticket first. A typo'd number fails before anything is created, so you never end up with a half-made worktree named after nothing.
Fetches origin/main and branches off that — not local main, which is stale in every worktree in this repo and is the usual cause of a "why is this diff so large" PR.
Creates a sibling worktree at ../salesagent-<ticket>.
Seeds an isolated beads DB into .beads-local/ with sqlite3 .backup. cp is wrong here: the shared DB is normally live with a WAL sidecar and a plain copy can capture a torn page.
Writes .envrc exporting BEADS_DB, with the mirror-back command baked in — see the warning below.
Writes TICKETS so /prime needs no arguments.

The beads warning, because it has already cost work

bd resolves its database through git-common-dir, so without isolation every worktree writes the shared database and parallel agents clobber each other. That is why this exists.

But isolated is not the same as disposable. Tickets you create or close in a worktree live only in that worktree until mirrored. On PR #1728 six tickets — including the entire deferral record for one ticket — existed nowhere else and were caught by hand minutes before teardown.

So .envrc carries the mirror command, and you run it before you finish:

bd export --id "<ids>" -o /tmp/beads-mirror-<ticket>.jsonl
cd <main-checkout> && env -u BEADS_DB bd import -i /tmp/beads-mirror-<ticket>.jsonl

Read the full file on GitHub · 76 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.

ticket-start.sh 4.6 KB runs code

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.

2d ago First seen · 76 lines · 61 tokens per session scan A cdd534c5bbeb

Subscribe to this mod's changes

ticket-start is a skill published in the GitHub repository prebid/salesagent (37 stars, last pushed 2d ago), licensed Apache-2.0. It adds 61 tokens to every session and 743 once invoked, about $0.0003 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 2026-09-04.

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

cyrus-setup-repository

Add one or more Git repositories to Cyrus configuration so it can process issues from those repos.

cyrusagents/cyrus · 25 tokens

github-sync

Bidirectional synchronization of epics and tasks with GitHub issues, labels, and relationships.

a5c-ai/babysitter · 0 tokens

github-sync-helper

General GitHub basic operations + automation for GitHub platform objects (Issues/Labels/Milestones/Releases/Actions) in the Minis environment. This skill must be triggered when the user mentions any basic Git/GitHub operation or workflow, including "how to use GitHub," clone, init, remote, branch, commit, push, pull…

OpenMinis/MinisSkills · 124 tokens

salesagent: Skill for Claude Code