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 atretyak1985/swarmery --skill jira-triagegit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/jira-triage)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/jira-triage"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/jira-triage/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/atretyak1985/swarmery/jira-triage"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/jira-triage.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 | $0.00095 | $0.05282 |
| Opus 5 | $0.00048 | $0.02641 |
| Sonnet 5 | $0.00019 | $0.01056 |
| Haiku 4.5 | $0.00010 | $0.00528 |
Grade A, and why
jira-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 9d 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 — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Turn a ticket that jira-access-preflight has already smoke-read into a
decision: is this actually done, genuinely not reproducing, in need of real
work, impossible to even attempt yet, or too large to touch under
/jira-fix's autonomy budget? This skill is the only place in jira-pack
that runs the evidence step and assigns a verdict — jira-writeback
downstream only renders and posts whatever this skill decided.
A tracker holds two kinds of work, and only one of them reproduces. A
defect describes behavior that exists and is wrong; a change (feature, task,
improvement) describes behavior that does not exist yet. Running a defect's
reproduction against a change ticket returns green — the suite is fine, the
feature simply isn't there — and reading that green as "the reported behavior
did not occur" would classify unimplemented work as cannot-reproduce and
move it to QA. Step 1b exists to make that outcome unreachable: every ticket
is classified before the evidence step, and the evidence step is chosen by
that class.
When to use
Called by @jira-task-runner's step 4, strictly after jira-config (working
repo + jira.repro.* resolved), jira-access-preflight (tools pinned,
cloudId resolved, ticket smoke-read already succeeded), and
swarmery-board-card (card already sitting in in_progress). Never run this
skill's reproduction step against an unvalidated repo path or before access
preflight has passed — a failed smoke-read means there is no ticket to triage
yet.
Step 1 — parse the ticket
Call getJiraIssue with
fields: ["summary", "description", "status", "issuetype", "labels", "components", "comment"]
(a fuller read than preflight's own smoke-read, which only pulled
summary/status/description/comment). Extract:
- the problem description and any "Steps to reproduce" section or its equivalent (numbered list, a fenced repro script, a linked test);
- expected vs. actual behavior, as stated;
- any file paths, stack traces, or commit references mentioned in the description or comments;
- prior comments — read every one. A previous comment often already says
"fixed in
<commit>" or "duplicate of<KEY>"; missing this is the most common way a run wastes its reproduction budget on an already-closed question.
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.
- 9d ago First seen · 378 lines · 95 tokens per session scan A 7bae14d02c4b
jira-triage is a skill published in the GitHub repository atretyak1985/swarmery (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 95 tokens to every session and 5,282 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
factory-triage
Triage a Factory work item's issue — trace history, understand architecture, diagnose root cause, then advance the stage.
github-fix-issue
Analyze and fix GitHub issues in the current repository, including issue research, scoped implementation, and testing. Use when the user asks to fix, investigate, or work on a GitHub issue by number or URL. Create branches, commits, pushes, or pull requests only when the user explicitly requests those delivery actions.
reframe-voice
Write, rewrite, or review content in the evidence-led reframe voice style. Use when the user explicitly asks to write in "reframe voice" or "reframe style". Do NOT use for general writing tasks.
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
propose-issue
Use when the user asks to propose an issue, file or open a bug report, or turn a reported defect into a tracked issue. Not for fixing the defect, triaging existing issues, or reviewing PRs.
execute
Execute phase — wave-based crew dispatch with critic gates and evidence-based verification.