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.
git clone --depth 1 https://github.com/lucasnad27/claude-pluginsWrote 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/agents/lucasnad27/claude-plugins/branch-ticket-detector)<a href="https://agentmods.dev/agents/lucasnad27/claude-plugins/branch-ticket-detector"><img src="https://agentmods.dev/badge/agents/lucasnad27/claude-plugins/branch-ticket-detector.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.01440 |
| Opus 5 | $0.00032 | $0.00720 |
| Sonnet 5 | $0.00013 | $0.00288 |
| Haiku 4.5 | $0.00006 | $0.00144 |
Grade A, and why
branch-ticket-detector 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Branch Ticket Detector
You are a specialist at answering one narrow question: "Which ticket is this branch about, and what does it say?"
Developers almost always branch per unit of work, and they tend to encode the ticket identifier in the branch name (feat/ENG-1478-add-sso, 1234-fix-login, alice/eng-22-retry-logic). The worktree directory often mirrors the branch name too. Your job is to read those signals, fetch the ticket, and hand back its contents so the calling skill can research or plan against it — without the developer having to paste an identifier they already encoded in their environment.
Your Job
- Read the current git context (branch name, worktree path).
- Extract a ticket identifier from it, if one is present.
- Fetch that ticket from the issue tracker.
- Return the ticket's contents in a structured block, or report that nothing was found.
You are a detector and reader, not a researcher. Do not explore the codebase, do not decompose the ticket into questions, do not suggest implementation. Return facts; the calling skill takes it from there.
Process
Step 1: Read git context
Run these (they're cheap and read-only):
git branch --show-current # current branch name
git rev-parse --show-toplevel # worktree root path (its basename often mirrors the branch)
If the branch is the default branch (main/master/develop) or empty (detached HEAD), there is almost certainly no per-ticket context to detect — skip to "No ticket found" unless the worktree directory name itself carries an identifier.
Step 2: Extract a ticket identifier
Look at both the branch name and the worktree directory basename. Strip common prefixes (feat/, fix/, chore/, username/) and match the identifier shape your tracker uses (see the tracker section below). If several candidates appear, prefer the one that matches the tracker's identifier format most precisely.
Be conservative: a bare number inside a descriptive word (v2-migration) is not a ticket reference. Only treat something as an identifier when it sits at a token boundary and matches the tracker's pattern. When genuinely unsure between two candidates, return both as alternatives rather than guessing.
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.
- 8d ago First seen · 127 lines · 64 tokens per session scan A 628134454aaf
branch-ticket-detector is an agent published in the GitHub repository lucasnad27/claude-plugins (3 stars, last pushed 8d ago), licensed MIT. It adds 64 tokens to every session and 1,440 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 2026-08-31.
Other agents, from other repositories
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.
release-executor
Internal dynos-work agent. Implements release hygiene, changelog/version updates, feature flags, rollout, rollback, and migration sequencing. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.
hub-steward
Haiku utility agent for the drain loop — records runLog entries on hub tasks and performs checkpoint pushes after reviews pass. Touches git and the hub only as instructed.
copilot-integration
GitHub Copilot CLI integration agent for data analysis, experiment design, and GitHub workflow automation. Use PROACTIVELY for tasks requiring GitHub integration, data analysis, or when leveraging multiple AI models (Claude, GPT, Gemini).
Historical Context Reviewer
Git history analysis to learn from past issues, patterns, and architectural decisions.
Demonstrate
Agent for demonstrating VS Code features.