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.
npx skills add big-emotion/agent-atelier --skill ticketgit clone --depth 1 https://github.com/big-emotion/agent-atelierWrote 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.
[](https://agentmods.dev/skills/big-emotion/agent-atelier/ticket)<a href="https://agentmods.dev/skills/big-emotion/agent-atelier/ticket"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/ticket/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.
<a href="https://agentmods.dev/skills/big-emotion/agent-atelier/ticket"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/ticket.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.03297 |
| Opus 5.5 | $0.00000 | $0.01319 |
| Sonnet 5.5 | $0.00000 | $0.00659 |
| Haiku 4.5 | $0.00000 | $0.00330 |
Grade A, and why
{{project_slug}}-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 1mo 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.
This is a copy
86% identical to project-standard-ticket — 76 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{{project_display_name}} Ticket
Take a single Jira ticket from link to merged-ready PR, locally and unattended.
This is the local, interactive, on-demand counterpart to Ferry (which runs the same lifecycle async/cloud via Jira Automation). It does not call Ferry; it does the work directly on the developer's machine. To avoid divergence with Ferry, the base branch, the PR target branch, and the review column are read from ferry.config.json at runtime — never hard-coded. The one deliberate divergence is the working-branch prefix: the config's working_branch_prefix names the namespace Ferry's automation owns (typically ferry/), so local runs stay out of it and use the human-style prefixes of the repo history instead ({{working_branch_prefix}}, fix/ — Step 5).
Operating mode — FULL AUTO
The user chose no confirmation gates. The skill runs the entire chain — assign → read → refine → sub-tasks → branch → implement → PR → Jira transition + comment — without stopping to ask.
"Full auto" removes confirmation prompts. It does not remove safety blockers: a small set of hard preconditions where proceeding would corrupt shared state or produce a broken PR. On a safety blocker the skill stops and reports — it does not guess or force through. These are listed under Preconditions and are non-negotiable.
When to Activate
- User pastes a Jira ticket URL (e.g.
https://<org>.atlassian.net/browse/KEY-123) or a bare issue key. - User says: "prends ce ticket", "implémente / traite ce ticket Jira", "fais ce ticket".
- User invokes
/{{project_slug}}-ticket <jira-url-or-key>.
Inputs
A single argument: the Jira ticket URL or issue key.
- Accept
.../browse/KEY-123,...selectedIssue=KEY-123,...?...&issueKey=KEY-123, or a bareKEY-123. - Extract the issue key with the regex
[A-Z][A-Z0-9]+-\d+. If zero or more than one distinct key is found, stop and ask the user for the exact key (ambiguous input is a safety blocker, not a design choice).
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.
- 1mo ago First seen · 197 lines · 0 tokens per session scan A dcbfec0fec8f
{{project_slug}}-ticket is a skill published in the GitHub repository big-emotion/agent-atelier (3 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,297 tokens. A static security scan graded it A with 0 findings. It is 86% identical to project-standard-ticket, differing in 76 lines, and is treated as a copy.
Other skills, from other repositories
bootstrap-working-agreements
Bootstrap a new repo with the full working-agreements + GitHub Project + CLAUDE.md hub-and-spokes setup in one pass. Use on a fresh repo, or on an existing repo that has no .claude/ tooling yet. Calls github-project-setup and split-claudemd as sub-steps; writes .claude/rules/working-agreements.md and a starter root…
add-azuredevops
Adds Azure DevOps connector to a Power Apps code app. Use when querying work items, creating bugs, managing pipelines, or making ADO API calls.
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
gitlab-devops
GitLab DevOps operations — issues, merge requests, CI/CD pipelines, repository browsing, labels, milestones, releases, and wiki management. Use when querying GitLab project status, monitoring pipeline executions, browsing repository files, creating issues for network findings, opening merge requests for config…
backlog
Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being…
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.