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 baseballyama/eslint-plugin-postgresql --skill issue-triagegit clone --depth 1 https://github.com/baseballyama/eslint-plugin-postgresqlWrote 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/baseballyama/eslint-plugin-postgresql/issue-triage)<a href="https://agentmods.dev/skills/baseballyama/eslint-plugin-postgresql/issue-triage"><img src="https://agentmods.dev/badge/skills/baseballyama/eslint-plugin-postgresql/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/baseballyama/eslint-plugin-postgresql/issue-triage"><img src="https://agentmods.dev/badge/skills/baseballyama/eslint-plugin-postgresql/issue-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00106 | $0.02426 |
| Opus 5.5 | $0.00042 | $0.00970 |
| Sonnet 5.5 | $0.00021 | $0.00485 |
| Haiku 4.5 | $0.00011 | $0.00243 |
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 1mo 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue triage
Triage a GitHub issue end to end: read it, classify it, label it, and run the workflow that matches its kind.
The user's GitHub handle is the operator (referred to as op below). When the
issue's author and op are different, "the author" means whoever opened the issue.
Operating principles
- Stay on the issue you were given. One issue per invocation. Don't sweep related issues unless the user asks.
- Confirm before public actions. Posting comments, applying labels, opening PRs, @-mentioning anyone: confirm the plan with the user before the first GitHub- visible action. After they approve, you can execute the rest of the plan without re-confirming each step.
- Never close the issue yourself. Triage is routing; closing is the maintainer's call.
- Don't @-mention people who aren't already in the thread. Specifically, the only person you may @-mention is the issue's author, and only when you actually need information from them.
- Match the issue's language. If the issue is in Japanese, your comment is in Japanese. If English, English. Don't switch languages on the author.
Step 0 — Locate the issue
Resolve what you're working on:
gh issue view <num> --repo <owner>/<repo> \
--json number,title,body,labels,author,state,comments
If the user pasted an issue body inline rather than a number, work from that and confirm the issue number with the user before posting anything.
Read existing labels and comments before doing anything. Someone may have already started triaging. Don't duplicate or contradict prior work without addressing it.
Step 1 — Classify
One of: bug, enhancement (feature request), documentation, question,
dependencies, or other.
| Signal | Likely class |
|---|---|
| "throws", "wrong output", repro steps + expected vs actual | bug |
| "would be nice if", "support for X", "add an option to ..." | enhancement |
| "how do I ...", "is this supported?" | question |
| typo / wrong sample / link rot in README or docs | documentation |
| renovate / dependabot / lockfile bump | dependencies |
| spam / off-topic / unrelated repo | other (invalid) |
| CI flake or build error in the user's environment | usually question, unless reproducible against a clean checkout — then bug |
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.
- 1mo ago First seen · 242 lines · 106 tokens per session scan A 1bc721fd91fa
issue-triage is a skill published in the GitHub repository baseballyama/eslint-plugin-postgresql (11 stars, last pushed yesterday), licensed MIT. It adds 106 tokens to every session and 2,426 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.