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 andrewsrigom/agent-skills --skill github-triagegit clone --depth 1 https://github.com/andrewsrigom/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/andrewsrigom/agent-skills/github-triage)<a href="https://agentmods.dev/skills/andrewsrigom/agent-skills/github-triage"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/github-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/andrewsrigom/agent-skills/github-triage"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/github-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 | $0.00047 | $0.00526 |
| Opus 5.5 | $0.00019 | $0.00210 |
| Sonnet 5.5 | $0.00009 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
github-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 2mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Triage
Use this skill when the task is to sort, qualify, or prepare GitHub work.
Scope
- reviewing new issues
- categorizing bugs vs enhancements
- identifying missing information
- deciding whether an issue is ready for implementation
- summarizing next action for maintainers or agents
Default path
- Read the issue body, labels, and recent comments.
- Restate the problem in one line.
- Decide whether it is:
- bug
- enhancement
- question
- duplicate or out of scope
- Check the codebase only enough to understand the relevant domain and likely boundary.
- Recommend one next state:
- needs info
- ready to implement
- needs design
- not actionable
- If actionable, note the likely testable behavior and affected boundary.
When to deviate
- Investigate deeper only if the issue already looks actionable and the missing confidence is technical rather than descriptive.
- Escalate to design instead of implementation when the issue is really a product or UX decision.
- Close as duplicate or out of scope only when that state is defensible from the issue history or codebase context.
Guardrails
- Do not start implementing during triage.
- Do not over-investigate before deciding whether the issue is even valid.
- Keep the issue durable: describe behavior, not file paths.
- Separate “not enough information” from “not a real bug.”
Avoid
- jumping into code changes during triage
- over-reading the codebase before deciding whether the issue is valid
- confusing missing information with invalid reports
- writing triage notes that only make sense if the file layout never changes
Verification checklist
- the issue is restated in one clear sentence
- the category is explicit
- missing information, if any, is concrete
- the next state is chosen intentionally
- if actionable, the likely boundary and testable behavior are identified
Output Shape
When answering with this skill, prefer:
- issue summary
- category
- confidence level
- missing information, if any
- recommended next action
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.
- 2mo ago First seen · 76 lines · 47 tokens per session scan A 2d8515125702
github-triage is a skill published in the GitHub repository andrewsrigom/agent-skills (2 stars, last pushed 7mo ago), licensed MIT. It adds 47 tokens to every session and 526 once invoked, about $0.0002 per session on Opus 5.5. 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.
github-triage compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| github-triageandrewsrigom/agent-skills | Skill | 2 | 7mo ago | MIT | A | 47 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |