A step-by-step workflow for completing a Linear ticket from its details through a code change, tests, pull request, and ticket update. Linear is a tool for tracking development work and acceptance criteria.

Use it when given a ticket ID to fetch context, choose the right code area, create a branch, implement the smallest suitable change, run tests, draft a pull request, and update Linear.

It helps keep ticket work consistent and prevents important steps—such as checking requirements, testing, or recording the result—from being skipped.

How hoophq/hoop configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to hoophq/hoop. 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/hoophq/hoop/main/.claude/skills/fix-ticket/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/hoophq/hoop

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/hoophq/hoop/fix-ticket.svg)](https://agentmods.dev/skills/hoophq/hoop/fix-ticket)

Your own site

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

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 643 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	$0.00043	$0.00643
Opus 5	$0.00022	$0.00321
Sonnet 5	$0.00009	$0.00129
Haiku 4.5	$0.00004	$0.00064

Measured 7d ago against content hash a39d4cac6c13, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fix-ticket 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.

.claude/skills/fix-ticket/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix a Linear ticket

Input: a Linear ticket ID. Follow every step — this encodes the team's standard flow.

1. Context

Fetch the full ticket via the Linear MCP server (title, description, comments, branchName, acceptance criteria). If Linear MCP is not connected, ask the user to run /mcp to authenticate — do not guess the ticket content.
Identify which module the change belongs to: gateway/, agent/, client/, common/, tunnel/, or webapp_v2/ (the legacy webapp/ is frozen — only touch it if the ticket says so explicitly).
For frontend tickets with a Figma link, pull the design context via the Figma MCP before writing UI code.
If the ticket has no clear acceptance criteria and the change is not obvious, post ONE clarifying comment on the ticket (or ask the user) before writing code.

2. Branch

Prefer a dedicated worktree per ticket (claude --worktree <ticket-id> — see .claude/README.md for hoop-specific worktree notes).
Create the branch using Linear's branchName so Linear auto-links the PR. Base it on up-to-date main.

3. Implement

Smallest correct change that satisfies the ticket. Follow CLAUDE.md (route registration/middleware order for gateway API, packet dispatch patterns for agent, module conventions).
Commit messages start with the ticket ID: EVL-86: <summary>.

4. Validate

Go changes: make test-oss (it runs libhoop-map + generate-wasm itself). Fix failures caused by your change; never skip or weaken tests.
webapp_v2/ changes: npm run lint and npm run build must pass.
New gateway endpoints/migrations: check migration-check / breaking-change-check CI expectations before pushing.

5. Draft PR

Open with gh pr create --draft. Title: <ID>: <summary>. Body must contain:

## Ticket
<ticket ID only, e.g. DEP-147 — never a Linear URL>

## What & why
<2-6 lines>

## How to test
<exact commands + steps + expected result — write it so a teammate
 can validate the flow without asking anything>

## Risks
<what could break, or "low">

Read the full file on GitHub · 72 lines

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.

7d ago First seen · 72 lines · 43 tokens per session scan A a39d4cac6c13

Subscribe to this mod's changes

fix-ticket is a skill published in the GitHub repository hoophq/hoop (807 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 643 once invoked, about $0.0002 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 2026-08-30.

Git and workflow LLM Productivity Security Testing agent databases grpc proxy

meta-pre-commit-quality-gate

Run three quality gates (ruff + mypy + pytest) in parallel over the staged diff, then arbitrate a single BLOCK/APPROVE verdict. Use before committing changes locally when you want a comprehensive pre-commit gate beyond per-file linting — exactly the same gate set CI enforces.

opensquilla/opensquilla · 68 tokens

release

Prepare dynobox packages for release to npm. Use this skill whenever the user asks to release, publish, ship, bump, or cut a version of any dynobox package — including dry runs, version bumps, changelog updates, and git tagging. Also trigger when the user asks about the release process or wants to verify publish…

dynobox/dynobox · 71 tokens

commit

Prepare and create git commits for dynobox. Use this skill whenever the user asks to commit, create a commit, suggest a commit message, stage changes, or prepare changes for review. Also use it when the user asks whether the changelog should be updated before committing.

dynobox/dynobox · 59 tokens

hoop: Skill for Claude Code