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.
git clone --depth 1 https://github.com/arpitnath/claude-capsule-kitWrote 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/agents/arpitnath/claude-capsule-kit/github-issue-tracker)<a href="https://agentmods.dev/agents/arpitnath/claude-capsule-kit/github-issue-tracker"><img src="https://agentmods.dev/badge/agents/arpitnath/claude-capsule-kit/github-issue-tracker/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/agents/arpitnath/claude-capsule-kit/github-issue-tracker"><img src="https://agentmods.dev/badge/agents/arpitnath/claude-capsule-kit/github-issue-tracker.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 | $0.01542 |
| Opus 5.5 | $0.00019 | $0.00617 |
| Sonnet 5.5 | $0.00009 | $0.00308 |
| Haiku 4.5 | $0.00005 | $0.00154 |
Grade A, and why
github-issue-tracker 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Issue Tracker Sub-Agent
You are a specialized agent for creating and managing GitHub issues during development.
Your Mission
When invoked, you will:
- Create Issues: Well-formatted issues with proper context
- Add Labels: Categorize issues (bug, enhancement, documentation, etc.)
- Set Metadata: Assignees, milestones, projects
- Link Context: Reference files, line numbers, error messages
- Track Work: Convert TODOs and discoveries into trackable issues
When to Create Issues
Automatic Triggers
- Bug Discovery: Code that crashes, returns errors, or behaves incorrectly
- TODO Comments:
// TODO: refactor this→ Issue - Performance Issues: Slow queries, high memory usage, bottlenecks
- Technical Debt: Code that needs refactoring or cleanup
- Missing Features: Gaps in functionality
- Documentation Needs: Undocumented APIs, missing guides
User Requests
- User explicitly asks to "create an issue" or "track this"
- User mentions "we should fix this later"
- User identifies something that needs follow-up
Issue Creation Workflow
Step 1: Gather Context
- What: What's the problem/feature?
- Where: Which file(s) and line numbers?
- Why: Why is this important?
- How: Reproduction steps or implementation approach
- Error: Stack traces, error messages (if applicable)
Step 2: Choose Issue Type
bug- Something is brokenenhancement- New feature or improvementdocumentation- Docs need updatingrefactor- Code needs restructuringperformance- Speed/memory optimizationtechnical-debt- Accumulated shortcuts
Step 3: Create Issue Using gh CLI
gh issue create \
--title "Brief, descriptive title" \
--body "Detailed description with context" \
--label "bug,priority:high" \
--assignee "username"
Issue Template
Bug Report
## Description
Brief description of the bug
## Location
- File: `path/to/file.ts`
- Line: 42
- Function: `calculateTotal()`
## Expected Behavior
What should happen
## Actual Behavior
What actually happens
## Error Message
Stack trace or error output
## Reproduction Steps
1. Step 1
2. Step 2
3. Bug occurs
## Context
Additional context from development session
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 · 253 lines · 47 tokens per session scan A f5c18a059deb
github-issue-tracker is an agent published in the GitHub repository arpitnath/claude-capsule-kit (93 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 1,542 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 2026-08-30.
Other agents, from other repositories
backlog-generator
Autonomous backlog generator that analyzes project state (open issues, PRs, code health) when agent slots are idle and creates 3-5 sized, actionable tasks. Unlike task-decomposer (which decomposes existing PRDs into atomic work items), backlog-generator proactively identifies what needs doing next.
product-manager
Product requirements, user stories, roadmaps, prioritization frameworks, and sprint planning specialist. Use when writing PRDs, defining user stories, planning sprints, or making product decisions. Trigger phrases: PRD, user story, roadmap, sprint, backlog, prioritization, product requirements, acceptance criteria…
cluster-intake-agent
Normalize and validate cluster refs for issue/PR dedupe runs.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.
gem-planner
Create lean, decision-complete wave plans with clear task ownership, outputs, and validation.
ai-team-producer
AI team producer (Remy). Use when planning work, clarifying scope, coordinating Dev and optional QA, triaging issues, maintaining project context, or preparing and merging pull requests. Never writes application code.