wick-tickets

wick-tickets is a skill for Claude Code, Codex from yogasw/wick. It costs 89 tokens per session (861 once invoked), scanned A, original, MIT.

A ticket-management workflow for coding sessions. A ticket is a unit of work, while a session is one conversation about that work, so several sessions can share the same ticket.

In plain words
What is it for?
Use it to open and list tickets, inspect their details, track status, manage assignees, and continue work on a named ticket.
Why use it?
It keeps the work's status, assignee, fields, and notes in one place, even when a conversation needs to be abandoned and continued elsewhere.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to open and list tickets, inspect their details, track status, manage assignees, and continue work on a named ticket.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yogasw/wick/wick-tickets
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 yogasw/wick --skill wick-tickets
Clone the repo
git clone --depth 1 https://github.com/yogasw/wick

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 wick-tickets

README.md
[![agentmods](https://agentmods.dev/badge/skills/yogasw/wick/wick-tickets.svg)](https://agentmods.dev/skills/yogasw/wick/wick-tickets)
Your own site
<a href="https://agentmods.dev/skills/yogasw/wick/wick-tickets"><img src="https://agentmods.dev/badge/skills/yogasw/wick/wick-tickets.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 861 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 $0.00089 $0.00861
Opus 5 $0.00044 $0.00430
Sonnet 5 $0.00018 $0.00172
Haiku 4.5 $0.00009 $0.00086

Measured 7d ago against content hash 868f7c2612db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

wick-tickets 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.

internal/agents/skillsync/builtin/wick-tickets/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tickets

A ticket is a unit of work. A session is one conversation about it, and a ticket can hold several. That separation is the point: a conversation that has gone wrong can be abandoned and replaced without losing the work, because the ticket keeps the status, the assignee, the fields, and the notes.

Use the tickets connector. Notes are a different connector — see the wick-notes skill for those.

Know what you are on

Your prompt already names this session's ticket — its id, title, status, and an excerpt of its description — so when the user starts talking, assume the conversation is about that ticket unless they say otherwise.

ticket_get with no arguments returns the ticket this session is attached to, in full:

ticket_get

Call it when you need what the prompt excerpt does not carry — the full description (body), the fields, who it is assigned to, how many other sessions are on it.

ticket_list shows a project's tickets, newest first, and takes an optional status filter. Use it to answer "what is open?" without opening the board — and to find tickets related to this one: list, then ticket_get the candidates whose titles look relevant and compare their descriptions.

Keep the status honest

The status is what a person scanning the board reads, so move it when reality moves:

ticket_update status=in_progress     # you started work
ticket_update status=waiting         # blocked on a human or something external
ticket_update status=done            # finished

Those are the built-in defaults — a project can rename or replace its columns entirely. Call ticket_settings_get or ticket_list if you are unsure what this board's statuses are; ticket_update only accepts this project's own.

Every update also resets the project's stale-follow-up timer. If a follow-up message woke you, update the ticket before you finish, or you will be woken again for the same reason.

ticket_update also takes title, body (the markdown description — an empty string clears it), assignee (an empty string unassigns), and fields as a JSON object of the project's own field values. Only what you pass changes. Keep the description current the same way you keep status honest: when the understanding of the work changes, rewrite body so the next session starts from the truth.

Read the full file on GitHub · 93 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.

  1. 7d ago First seen · 93 lines · 89 tokens per session scan A 868f7c2612db

Subscribe to this mod's changes

wick-tickets is a skill published in the GitHub repository yogasw/wick (5 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 861 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 2026-08-31.