GitHub Issue → Claude Code Prompt Pack
Pricing
Pay per usage
GitHub Issue → Claude Code Prompt Pack
gh-issue-to-claude-prompts is an Apify Actor that picks the top open issues from any GitHub repo and returns ready-to-paste Claude Code prompts enforcing a 6-step workflow: investigate, plan-approval, implement, test, verify, stop. One paste, one fix.
Pricing
Pay per usage
Rating
0.0
(0)
Developer
Yanlong Mu
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
20 days ago
Last modified
Categories
Share
gh-issue-to-claude-prompts is an Apify Actor that picks the top open issues from any GitHub repo and returns ready-to-paste Claude Code prompts that enforce a 6-step workflow (investigate → plan-approval → implement → test → verify → stop). It turns a maintainer's Monday backlog or a contributor's bounty hunt into a stack of correctly-framed agent prompts in seconds.
Best for / Not for
| ✓ Best for | ✗ Not for |
|---|---|
| OSS maintainers triaging the top 10 issues in one batch | Private repos (anonymous GitHub API only in the public version) |
Contributors hunting bounty / good first issue labels across many repos | Auto-merging fixes — prompts enforce a human approval gate by design |
| Teams standardizing "every Claude Code task starts from this template" | One-off "just fix this bug" prompts where investigation isn't needed |
Example input → output
Input:
{"githubRepo": "anthropics/claude-code","maxIssues": 10,"labels": "bug,good first issue","sortBy": "most-commented"}
Output (one row, truncated):
{"issueNumber": 60835,"issueTitle": "Tests written by Claude wrote to production shared infrastructure (NAS) without isolation","issueUrl": "https://github.com/anthropics/claude-code/issues/60835","labels": "model, bug","prompt": "I'm working on issue #60835 in anthropics/claude-code...\n\n1. First explore the relevant code...\n2. Outline a fix plan with specific files to change..."}
A bundled prompt-pack.md with all prompts as paste-ready blocks is also written to the Key-Value Store.
FAQ
Does this work with Claude Code?
Yes — the prompts are written specifically for Claude Code's plan-mode / approval workflow. They tell the model to STOP after step 2 (plan) and wait for human approval before editing. The 6-step structure also works with Cursor, Codex CLI, Aider, and Cline.
Is it free?
The first 10 prompts (one batch) are a free trial. After that the Actor uses Apify's pay-per-event model at $0.02 per prompt generated ($0.20 per 10-issue batch, $1 for a 50-issue batch).
Does it scan private repos?
Not yet — the public version uses anonymous GitHub API. A future version may accept a githubToken input via Apify secrets for private-repo access.
Can I run it in CI?
Yes. Schedule the Actor via Apify cron (e.g. every Monday 09:00) to auto-generate a fresh backlog pack each week. Or trigger it from a GitHub Action when a new bounty issue is opened.
Output format?
JSON dataset (one row per issue with structured prompt field) and a downloadable Markdown bundle (prompt-pack.md) you can paste into Claude Code one block at a time. Both available from the Apify Storage tab.
Rate limits?
GitHub anonymous API is capped at 60 req/hour. Each prompt costs ~1 API call, so 50 issues = 50 calls. Small repos work fine; very busy repos should be run off-peak.
Will the prompts work with Cursor / Codex / Aider / Cline?
The 6-step structure works with any agentic coding tool. Paste into whichever you use. The prompts are framework-agnostic.
Why do prompts insist on "stop and ask before editing"?
Because false-completion + skip-verify is the #1 source of bad merges in agent-driven dev. See verify-before-stop for the Stop-hook companion that enforces this at the workflow level.
How to use
- Paste a GitHub repo as
owner/repo(e.g.anthropics/claude-code) - Set Max issues (default 10, max 50)
- (Optional) Filter by labels (e.g.
bug,good first issue) - Pick sort criterion: most-commented (default), newest, or most reactions
- Click Start
- Download
prompt-pack.mdfrom the Storage tab → Key-Value Store - Open Claude Code in the target repo's directory, paste any prompt block, watch it work
Input
githubRepo(required) —owner/repoformatmaxIssues— top N open issues (default 10, max 50)labels— filter by labels (comma-separated)sortBy—most-commented/newest/reactions
Pricing
Pay-per-event model:
- First 10 prompts: free trial
- Per-prompt rate: $0.02 per prompt generated
- Per-batch (10 prompts): $0.20
- Cost estimate: $0.20 for a 10-issue batch, $1 for a 50-issue batch
Tips
- Public repos only. GitHub anonymous API is rate-limited to 60 req/hour — small repos work fine; for very busy repos run during off-peak.
labelsis powerful. Filter bybountyto find paid OSS work, orgood first issueto onboard new contributors.- Combine with bounty platforms. Many Algora-listed bounty repos use the
💰 bountylabel — setlabels: bountyand you get a paid-work pipeline.
Support
Issues / feature requests: open in the Issues tab on the Apify console.
Built by Ian Mu — github.com/ianymu — author of verify-before-stop.