From bugflow
Generate minimal-risk FE implementation plan for a bug. Use when bug workflow is started, verdict is FE/MIXED, and implementation plan is needed. Requires existing state file.
How this skill is triggered — by the user, by Claude, or both
Slash command
/bugflow:bug-planThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Configuration Required**: This skill requires project configuration. If `.claude/bugflow/config/environment.json` does not exist, prompt the user to run `/bugflow:bug-setup` first.
Configuration Required: This skill requires project configuration. If .claude/bugflow/config/environment.json does not exist, prompt the user to run /bugflow:bug-setup first.
Generate a minimal-risk frontend implementation plan with history-aware revision loop.
/bug-plan <bug_id> - Generate or revise implementation plan for a bug
FE or MIXED (not BE-only)VERDICT, VERIFY_FAIL, PLAN_FE, or VALIDATEOn validation failure: Archive plan, extract anti-patterns, loop (max 3). See REVISION-LOOP.md.
| Agent | Purpose |
|---|---|
| fe-implementer-planner | Generate minimal-risk implementation plan |
| test-spec-generator | Generate structured test specification |
| plan-validator | Validate plan quality (pass: score >= 70) |
VERDICT/VERIFY_FAIL
↓
[Planning Loop]
↓
score >= 70?
/ \
YES NO → [Archive + Extract anti-patterns]
↓ ↓
VALIDATE [Loop again, max 3]
↓ ↓
DONE AWAITING_APPROVAL (escalate)
| Output | Path |
|---|---|
| Dossier | <paths.dossierDir> from project config (default: docs/bugflow)/bug-.md (IMPLEMENTATION STRATEGY section) |
| State | <paths.stateDir> from project config (default: .bugflow)//state.json |
| Plan | <paths.stateDir> from project config (default: .bugflow)//context/plan.json |
| History | <paths.stateDir> from project config (default: .bugflow)//context/plan-history/*.json |
npx claudepluginhub konstantilieris/bugfow_pluginTransforms high-level ideas, feature descriptions, and bug reports into structured implementation plans. Integrates with brainstorm docs and local codebase research.
Guides writing or updating detailed plans for Claude Code sessions, assessing component readiness, filling knowledge gaps, defining testing strategies, and verifying hypotheses.
Categorizes plan review findings as fixable, false positive, deferrable, or needing human input, then applies fixes and produces a verdict report.