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 stark-ai-de/agent-skills --skill issue-triagegit clone --depth 1 https://github.com/stark-ai-de/agent-skillsWrote 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/stark-ai-de/agent-skills/issue-triage)<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/issue-triage"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/issue-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/stark-ai-de/agent-skills/issue-triage"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/issue-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 | $0.00049 | $0.00741 |
| Opus 5 | $0.00024 | $0.00370 |
| Sonnet 5 | $0.00010 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
issue-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 12d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Triage
Goal
Classify issues into actionable maintainer states, propose labels and responses, and identify what is needed before an agent or human should work on them.
When to use
- The user asks to triage GitHub, GitLab, Linear, or markdown issues.
- An inbox needs labels, status, duplicate detection, or missing information checks.
- A vague issue needs to be split into smaller work items.
When not to use
- The user asks for implementation rather than issue classification.
- The task is reviewing a pull request; use
pr-review. - The issue appears security-sensitive and should go through private reporting first.
Inputs
- Issue title, body, comments, labels, assignees, linked PRs, and project state.
- Repository docs, contribution rules, issue templates, and label conventions.
- Live tracker data when the user asks for real issue changes.
Inputs to inspect
- Inspect issue content, linked code/docs, existing labels, and tracker state needed to classify the issue.
- Check repository triage conventions before inventing labels.
Process
- Read the issue and linked context.
- Determine category: bug, feature, docs, question, duplicate, wontfix, maintenance, or security.
- Determine readiness: needs reporter, needs maintainer, ready for agent, ready for human, blocked, or duplicate.
- Propose labels and a concise maintainer response.
- Split broad issues into concrete follow-up issues when needed.
- Ask for approval before applying labels, closing, assigning, or editing issues unless the user explicitly authorized those actions.
Workflow
Use the process above to produce a proposed triage result first. Apply live issue changes only when the user has explicitly authorized that action.
Decision points
- If reproduction steps are missing for a bug, mark
needs-info. - If expected behavior is a product decision, mark
needs-maintainer. - If scope and validation are clear, mark
ready-for-agent. - If the report may be security-sensitive, avoid public detail and escalate to the security policy.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 101 lines · 49 tokens per session scan A da2929d82667
issue-triage is a skill published in the GitHub repository stark-ai-de/agent-skills (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 49 tokens to every session and 741 once invoked, about $0.0002 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
workspace
Multi-repo workspace coordinator for shared team context. Initialize .adlc/ structure, configure .gitignore, discover child repos, link them as Git submodules, and audit workspace health. Use --init for first-time setup, default mode for ongoing auditing.
product-roadmap
Track milestone progress across four layers of truth — decision state (PDR status), execution state (live issue tracker via MCP), evidence state (code-vs-PDR verification), and gate state (milestone gates). Shows honest completion, done-means warnings, and updates status only when all layers are green. Use for weekly…
product-clarify
Refine and validate Product Decision Records through targeted clarification questions. Review PDR completeness, detect conflicts, approve decisions, and update status to Accepted. Use before /product-implement.
status
Show active or recent Claude Code jobs in this repository, or detailed status for a specific job id. Args: [job-id], --wait, --timeout-ms , --poll-interval-ms , --all. Use for tracked-job inspection, not setup or result retrieval.
session-close
Close a coding-agent session with durable repository state, proportional verification, documentation reconciliation, and a useful handoff. Use when the user says close out, wrap up, end session, session report, doc sync, preserve work, or asks for a final commit and push before stopping.
completion-report
Write a completion report with files changed, tests run, results, skipped checks, docs updated, remaining risks, and release readiness notes. Use when recording evidence that a task or feature is complete and ready for review.