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 qte77/claude-code-plugins --skill triaging-issuesgit clone --depth 1 https://github.com/qte77/claude-code-pluginsWrote 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/qte77/claude-code-plugins/triaging-issues)<a href="https://agentmods.dev/skills/qte77/claude-code-plugins/triaging-issues"><img src="https://agentmods.dev/badge/skills/qte77/claude-code-plugins/triaging-issues/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/qte77/claude-code-plugins/triaging-issues"><img src="https://agentmods.dev/badge/skills/qte77/claude-code-plugins/triaging-issues.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 | $0.00061 | $0.00779 |
| Opus 5.5 | $0.00024 | $0.00312 |
| Sonnet 5.5 | $0.00012 | $0.00156 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
triaging-issues 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 21d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage GitHub Issues
Filter: $ARGUMENTS (optional label or keyword; empty = all open issues)
Read-only: never label, comment on, or close issues — present the plan; acting on it is a separate, explicit step.
Step 1: Fetch issues
gh issue list --state open --limit 200 --json number,title,author,labels,createdAt,updatedAt
If gh is missing or unauthenticated, stop and say so — do not guess the backlog. Apply the
filter if given. Read bodies (and comments) with gh issue view <N> --json body,comments.
Step 2: Cluster by concern
Group issues by the concern they actually address (e.g. CI gates, a plugin's behaviour, docs, proposals needing a decision) — derive clusters from the content, not a fixed taxonomy. Note dependencies (X blocks Y) and duplicates.
Step 3: Score each issue
| Dimension | Scale |
|---|---|
| ROI | H / M / L — user-visible impact, bugs breaking installs/runs rank highest |
| Effort | S < 0.5 d · M 1–2 d · L > 2 d — from the actual code, never estimated blind |
| Risk / deps | what could break, what must land first, what needs an owner decision |
Tier: P0 do now (high ROI, low effort) · P1 next · P2 later / needs scoping · P3 close or won't-do (with evidence).
For large backlogs, fan out one read-only subagent per cluster (Agent tool; or
cc-meta:orchestrating-parallel-workers if installed) and ground effort estimates by reading the
relevant code (codebase-tools:researching-codebase if installed).
Step 4: Verify before asserting
The step triage most often gets wrong:
- "Already fixed" / "superseded" / "close it" needs file-level evidence — the current file on the default branch or the commit that fixed it. A plausible commit message is not evidence.
- Re-check any count you report (files, skills, affected items) at source; say how you counted.
- Verify vendor/library claims against a first-party source.
- A subagent's verdict is a hypothesis: spot-check the load-bearing ones yourself.
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.
- 21d ago First seen · 70 lines · 61 tokens per session scan A 888a8f779cf8
triaging-issues is a skill published in the GitHub repository qte77/claude-code-plugins (3 stars, last pushed 4d ago), licensed Apache-2.0. It adds 61 tokens to every session and 779 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 2026-09-26.
Other skills, from other repositories
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
sprint-plan
Plan a sprint with capacity estimation, story selection, dependency mapping, and risk identification. Use when preparing for sprint planning, estimating team capacity, selecting stories, or balancing sprint scope against velocity.
review-resume
Comprehensive PM resume review and tailoring against 10 best practices including XYZ+S formula, keyword optimization, job-specific tailoring, and structure. Use when reviewing a PM resume, preparing for job applications, or improving resume impact.
job-stories
Create job stories using the 'When [situation], I want to [motivation], so I can [outcome]' format with detailed acceptance criteria. Use when writing job stories, creating JTBD-style backlog items, or expressing user situations and motivations.
stakeholder-map
Build a stakeholder map using a power/interest grid, identify communication strategies per quadrant, and generate a communication plan. Use when managing stakeholders, preparing for a launch, aligning cross-functional teams, or planning stakeholder engagement.
wwas
Create product backlog items in Why-What-Acceptance format — independent, valuable, testable items with strategic context. Use when writing structured backlog items, breaking features into work items, or using the WWA format.