From hatch3r
Guides 8-step agentic workflow for issues/work items: parse issue, load skills, read specs, plan, delegate to sub-agent, implement, test, open PR/MR, address review. Activates on issue mentions.
npx claudepluginhub hatch3r/hatch3rThis skill uses the workspace's default tool permissions.
When assigned an issue or work item (GitHub Issue, Azure DevOps Work Item, or GitLab Issue — check `platform` in `.agents/hatch.json`), follow these 8 steps in order:
Generates detailed GitHub issues with TDD plans, acceptance criteria, technical specs, error handling, and agent instructions for autonomous PR lifecycle management.
Resolves GitHub issues via triage, root cause analysis, test-driven development, branch management, testing, and pull request creation following CI/CD practices. Activated for issue resolution workflows.
Resolves GitHub issues through triage, root cause analysis, TDD, branch management, testing, and CI/CD-compliant pull requests. Ideal for team workflows on bugs and features.
Share bugs, ideas, or general feedback.
When assigned an issue or work item (GitHub Issue, Azure DevOps Work Item, or GitLab Issue — check platform in .agents/hatch.json), follow these 8 steps in order:
Task Progress:
- [ ] Step 1: Parse the issue
- [ ] Step 2: Load the issue-type skill
- [ ] Step 3: Read relevant specs
- [ ] Step 4: Produce a plan
- [ ] Step 5: Implement
- [ ] Step 6: Test
- [ ] Step 6b: Browser verification (if UI)
- [ ] Step 7: Open PR
- [ ] Step 8: Address review
Navigate to the matching skill based on issue type:
| Issue Type | Skill |
|---|---|
| Bug report | hatch3r-bug-fix |
| Feature request | hatch3r-feature |
| Code refactor | hatch3r-refactor |
| Logical refactor | hatch3r-logical-refactor |
| Visual refactor | hatch3r-visual-refactor |
| QA E2E validation | hatch3r-qa-validation |
Load only the specs relevant to the issue area. See the spec mapping table in the project context rule.
Also check project ADRs for architectural constraints.
Output a structured plan before writing code:
Every issue MUST be delegated to a dedicated hatch3r-implementer sub-agent — never implement inline. The board-pickup command orchestrates this automatically; if running issue-workflow standalone, apply the pattern that matches your scenario:
| Scenario | Pattern |
|---|---|
| Single issue | Spawn one hatch3r-implementer sub-agent via the Task tool with issue number, body, acceptance criteria, issue type, researcher output, and spec references. Await result. |
| Epic with sub-issues | Load references/delegation-patterns.md — Pattern 2 |
| Batch of standalone issues | Load references/delegation-patterns.md — Pattern 3 |
| Plain chat with multiple tasks | Load references/delegation-patterns.md — Pattern 4 |
The implementer sub-agent protocol is defined in the hatch3r-implementer agent. Each sub-agent handles its own implementation and testing but does NOT create branches, commits, or PRs.
Skip this step if the issue has no user-facing UI changes.
board.defaultBranch from .agents/hatch.json (fallback: "main").platform in .agents/hatch.json):
gh pr create --base {defaultBranch} --head {branch} --title "..." --body "..."az repos pr create --source-branch {branch} --target-branch {defaultBranch} --title "..." --description "..."glab mr create --source-branch {branch} --target-branch {defaultBranch} --title "..." --description "..."Stop and ask when: