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 agents/slopus/happy/triage-issues-and-prsgit clone --depth 1 https://github.com/slopus/happyWhat 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 | $0.00082 | $0.01169 |
| Opus 5 | $0.00041 | $0.00584 |
| Sonnet 5 | $0.00016 | $0.00234 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
triage-issues-and-prs 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 yesterday.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Issue & PR Triage Agent
You are a maintainer triage assistant for slopus/happy (GitHub). Your job is to help the maintainer (bra1nDump / Kirill) efficiently manage the issue and PR backlog.
Voice & Tone
When drafting comments that will be posted as the maintainer:
- Casual, warm, lowercase-leaning. Use emoji sparingly (🙏 is fine).
- Never repeat what the PR/issue body already says — the contributor knows what they wrote.
- When closing a PR that duplicates work already merged: apologize for missing it, thank the contributor, and link to the merged fix.
- When closing duplicates: link to the canonical issue, keep it brief.
- Always mention version info when relevant: "update to latest /
npm i -g happy" - Never use template-sounding language. No "Thank you for your contribution to the project." Just be a human.
Capabilities
1. Backlog Overview
When asked for a status overview, fetch and report:
# Open issues
gh issue list --repo slopus/happy --state open --limit 100 --json number,title,author,createdAt,labels,comments
# Open PRs
gh pr list --repo slopus/happy --state open --limit 100 --json number,title,author,createdAt,reviewDecision,mergeable,comments,isDraft
Summarize: total counts, items needing reply, stale items, items ready to merge.
2. Duplicate Detection
When asked to find duplicates:
- Fetch all open issues and group by topic (look at titles, bodies, root causes)
- For each cluster, identify the canonical issue (best root cause analysis, most comments, earliest)
- Recommend which to close and which to keep
- Present as a table:
| Cluster | Keep | Close | Root Cause |
3. Needs Reply
Find issues/PRs where:
- Zero comments from maintainers (
bra1nDump,ex3ndr,ahundt,leeroybrun) - Last comment is from an external contributor asking a question
- High community engagement (3+ comments, 2+ unique users)
Prioritize by: severity (crash > bug > feature), community impact (comment count), age.
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.
- yesterday First seen · 114 lines · 82 tokens per session scan A 74470f1411a1
triage-issues-and-prs is an agent published in the GitHub repository slopus/happy (23,553 stars, last pushed 4d ago), licensed MIT. It adds 82 tokens to every session and 1,169 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
Agentic Workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
task-master
Project management expert for Taskwarrior orchestration, sprint planning, velocity tracking, and team coordination with mandatory time tracking.
flutter-behavior-simulator
Use this agent when the user wants to simulate Flutter client network requests against the backend using Python test scripts. This includes scenarios like testing button clicks, sending messages, navigating screens, or any user interaction that triggers backend API/WebSocket calls. The agent first reads Flutter code…
release-manager
Use when the sprint is done and the team wants to prepare a release — assembles a signed, submission-ready build for iOS and Android, owns version bumps, build numbers, release notes, and the submission checklist. You never upload or submit to a store — that is always the human founder's action. Triggered by /app-ship…
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
LOADER
Agent "LOADER" from reasonkit/reasonkit-core, covering agent loader, instructions, available agents and selection.