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 agentmods add skills/matheuspavaneli/workbench/triage-tasknpx skills add matheusPavaneli/workbench --skill triage-taskgit clone --depth 1 https://github.com/matheusPavaneli/workbenchWhat 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 | $0.00051 | $0.00667 |
| Opus 5 | $0.00026 | $0.00333 |
| Sonnet 5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
triage-task scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
triage-task
All tracker access goes through one command. Never construct JQL, WIQL, URLs or field lists — the provider builds them from the resolved context.
python "${CLAUDE_PLUGIN_ROOT}/lib/wb.py" <args>
Steps
-
Resuming?
statusfirst. It lists every ticket with work in flight and the one command that moves each on, read off the artifacts on disk. If the ticket already has atriage.json, do not re-fetch it. -
No key given —
task list. Four columns, newest first. Show them and ask which one, unless the request already names one.No tracker in this repo?
task new "title" --type bug|feature|chore|supportrecords it in the local backlog and everything downstream works unchanged. Only local contexts accept it;wbsays so if the repo has a real tracker. -
Read it —
task get <KEY>. Writes.workflow/<KEY>/triage.jsonand prints it. Depth defaults to 1: the task, plus one line per linked item.- Use
--depth 0when the ticket is self-contained and links do not matter. - Use
--depth 2only when a blocker or a parent decides the approach. It fetches bodies for blocking and hierarchy links, never forrelates.
- Use
-
Go deeper only where it pays — the
_expandlist names what exists but was not included. Pass a handle back verbatim:task get <KEY> --expand comments:all. Do not compose handles; anything not in_expandis rejected. -
Check
_unmappedand_truncatedif present._unmappedmeans the tracker had a link type or field this version does not model — say so rather than guessing what it meant._truncatedmeans content was capped, and names the handle that would retrieve it. -
Report gaps before planning. If the ticket lacks acceptance criteria, a reproduction, or a decision someone else owns, list those questions plainly. A blocked-by link that is not Done is a gap, not a detail. Write them to
.workflow/<KEY>/questions.mdand say the ticket is not ready to plan.
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.
- 2d ago First seen · 58 lines · 51 tokens per session scan A 2677ab766405
triage-task is a skill published in the GitHub repository matheusPavaneli/workbench (1 stars, last pushed 10d ago), licensed MIT. It adds 51 tokens to every session and 667 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 skills, from other repositories
integration-rule-engine
A declarative routing engine that turns ticket / error attributes (reporter, label, project, area path, error class, environment) into a tag + AI agent + priority assignment, so cross-source workflows ("security tickets always go to the OWASP reviewer") stay out of code and in user-editable rules.
stale-ticket-triage
Replace the weekly "look at every ticket older than X days" meeting with a scheduled AI scan that picks close / snooze / keep per ticket plus a one-sentence reason, so a PM can bulk-approve in 90 seconds Monday morning.
azure-devops
Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check…
atlassian
Manage Jira issues and Confluence wiki pages in Atlassian Cloud. Use when: (1) searching/creating/updating Jira issues with JQL, (2) searching/reading/creating Confluence pages with CQL, (3) managing Jira workflows, transitions, and comments, (4) browsing Confluence spaces and page hierarchies. Supports OAuth 2.1 via…
pir-action-tracker
Parses Post-Incident Review (PIR) pages in a Confluence space, fetches live status from referenced Jira tickets, updates action item tables with current status and due dates, marks completed PIRs with a visual closure panel, and surfaces any overdue actions for follow-up. Designed for Customer Success, Support, and…
jira-administration
Complete JIRA project and system administration including projects, automation rules, permissions, users, notifications, screens, issue types, and workflows. Use when managing project structure, automating work, configuring team access, or setting up issue tracking.