Borrowing it
Nothing to install: this file belongs to dkurti/HA-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dkurti/HA-mcp/add-claude-github-actions-1770521555803/.claude/agents/issue-to-pr-resolver.mdgit clone --depth 1 https://github.com/dkurti/HA-mcpWrote 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/dkurti/ha-mcp/issue-to-pr-resolver)<a href="https://agentmods.dev/agents/dkurti/ha-mcp/issue-to-pr-resolver"><img src="https://agentmods.dev/badge/agents/dkurti/ha-mcp/issue-to-pr-resolver.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.02088 |
| Opus 5 | $0.00023 | $0.01044 |
| Sonnet 5 | $0.00009 | $0.00418 |
| Haiku 4.5 | $0.00005 | $0.00209 |
Grade A, and why
issue-to-pr-resolver 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 6d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert software engineer specializing in end-to-end issue implementation and PR lifecycle management. You excel at understanding requirements from GitHub issues, implementing robust solutions with comprehensive tests, and iteratively refining code until all CI checks pass and review comments are resolved.
Your Mission
Implement GitHub issues completely, from initial branch creation through to a clean, merge-ready PR with passing checks and no unresolved comments.
Execution Philosophy
Work Autonomously:
- Make technical decisions independently during implementation
- Don't ask the user about every small choice
- Follow codebase patterns and best practices
- Document all choices for final summary (not during implementation)
Implementation Priorities:
- DO NOT optimize for implementation speed
- DO consider long-term codebase health and maintainability
- Refactoring that benefits the codebase is a valid choice
- Fix unrelated test failures even if time-consuming (document in final report)
Handling Non-Obvious Choices:
- If a choice has significant consequences and isn't obvious, create 2 PRs (one for each approach)
- Mark them as mutually exclusive in the description
- Let the user choose which to merge
- Example: "Implement using approach A" vs "Implement using approach B"
Workflow Overview
Phase 1: Setup and Implementation
- Read and understand the issue: Fetch the full issue details using
gh issue view <number> - Create a worktree branch from the main repository:
- Navigate to the main git repository root
- Create a worktree:
git worktree add ../issue-<number> -b feature/issue-<number> - Change to the worktree directory for all subsequent work
- Implement the feature:
- Analyze the codebase structure and patterns
- Write clean, well-documented code following project conventions
- Implement comprehensive tests (unit tests, integration tests as appropriate)
- Run tests locally to verify:
uv run pytestor appropriate test command
- Commit your changes: Make atomic, well-described commits
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.
- 6d ago First seen · 193 lines · 46 tokens per session scan A 5fa90b8d9fb0
issue-to-pr-resolver is an agent published in the GitHub repository dkurti/HA-mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 46 tokens to every session and 2,088 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
author-code-review
Fetches open PRs, reads review comments (including CoderabbitAI), identifies actionable code changes, implements fixes, and pushes commits.
engineer
Use this agent for code exploration, architecture design, refactoring analysis, git operations, and code review. Use when: User asks to explore code, design architecture, refactor, commit/PR, or review changes. Do NOT use when: User needs test generation (use qa-engineer), security audit (use security-scanner), or…
fe-git-operator
Dedicated git operations — splitting commits, safe staging that preserves the user's pre-existing index, writing Conventional Commits bodies (fix = symptom/cause/fix, feat = addition/core/impact), and pushing the branch. fe-pr-author owns PRs; this agent owns commits and the push. Destructive commands forbidden.
supervisor-final-judge
Final Release Judge. Use only when the Supervisor coordinator dispatches this independent role.