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 PrabhdeepSingh/claude-plugins --skill ticket-triagegit clone --depth 1 https://github.com/PrabhdeepSingh/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/skills/prabhdeepsingh/claude-plugins/ticket-triage)<a href="https://agentmods.dev/skills/prabhdeepsingh/claude-plugins/ticket-triage"><img src="https://agentmods.dev/badge/skills/prabhdeepsingh/claude-plugins/ticket-triage.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 | $0.00114 | $0.02735 |
| Opus 5 | $0.00057 | $0.01367 |
| Sonnet 5 | $0.00023 | $0.00547 |
| Haiku 4.5 | $0.00011 | $0.00274 |
Grade A, and why
ticket-triage 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ticket triage — make the ticket good enough to build from
A vague ticket is not ready for a human or an agent. Somebody has to convert "login is broken sometimes" into a bounded problem with testable acceptance criteria, and doing that work before implementation starts is what keeps the build from becoming a guess. That conversion is this skill's only job, and the artifact it produces is the spec every later stage inherits.
The discipline that makes it useful is restraint. A triage pass that quietly starts fixing things destroys the human approval gate — the whole point is that a person reads the spec and decides whether it should be built at all.
How to apply this
Apply to $ARGUMENTS — the text typed after the invocation, a ticket id or URL. If that token appears literally or is empty, derive the ticket from context (the one /sonu:factory routed, or the one under discussion). With no ticket identifiable, say so and stop; never triage a ticket you had to guess at.
Load Skill(sonu:ticket-lifecycle) first for tracker resolution, the taxonomy, and the claim rules, then run sections 1 through 5 in order. Sections 1 and 2 are not optional preliminaries — a spec written without them is fiction.
1. Claim before anything else
Resolve the tracker, then claim the ticket before doing any work — the adapter's claim operation on the spec trigger: confirm it is present, clear it, confirm it is gone. Use the adapter's name for that trigger rather than a hardcoded string (a label on GitHub, Jira, and Linear; the trigger: field on a local ticket file). If the claim fails — including a trigger that was already absent — stop and report: another session holds this ticket.
Claim first, before the deep read in section 2. Reading a long ticket and inspecting code takes minutes, and every one of those minutes is a window where a second session can claim the same ticket and write a competing spec. Fetching just enough to identify the ticket is fine; the full read happens after the claim lands.
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 · 95 lines · 114 tokens per session scan A 34df56498f87
ticket-triage is a skill published in the GitHub repository PrabhdeepSingh/claude-plugins (3 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 2,735 once invoked, about $0.0006 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 skills, from other repositories
unity-coder
Use when implementing Unity C# code to follow proper coding guidelines, naming conventions, member ordering, and Unity-specific patterns.
unity-tests-write
Use when writing Unity tests, including EditMode tests, PlayMode tests, performance testing, and code coverage.
agent-teams
Set up and orchestrate Claude Code agent teams - multiple Claude Code instances working together with shared tasks, inter-agent messaging, and centralized management. Use when the user wants to (1) create or start an agent team for parallel work, (2) configure agent team settings like display mode or teammate mode or…
python-coder
Implements Python code following PEP 8, type hints, and project conventions. Use when implementing features designed by python-architect.
typescript-coder
Implements TypeScript/JavaScript code following established architecture and coding guidelines. Use when implementing features designed by typescript-architect.
python-testing
Python testing patterns with pytest including unit tests, integration tests, fixtures, mocking, and coverage. Use when writing Python tests.