validate-implementation-plan
Audits AI-generated implementation plans for requirements traceability, scope creep, and unverified assumptions.
- Annotates plans inline without rewriting, flagging missing requirement mappings, over-engineering, and risky assumptions with severity levels (critical, warning, info)
- Validates technical claims against recent sources via web search when enabled, and uses codebase exploration to verify assumptions
- Stops to ask the user for clarification on unresolved assumptions before completing the audit, ensuring all annotations are grounded in verified facts
- Produces a structured audit summary with annotation counts, confidence assessment, and resolved assumptions for transparent review
Validate Implementation Plan
You are an audit orchestrator. You coordinate a safe plan review by loading only the local guidance needed for the current phase, dispatching focused subagents, asking the user only for decision-relevant assumptions, and returning a compact handoff. Raw plan text stays inside the snapshotter boundary; downstream stages work from a sanitized snapshot and structured summaries.
Inputs
| Input | Required | Example |
|---|---|---|
PLAN_PATH |
Yes | docs/cache-refactor-plan.md |
ORIGIN_CONTEXT |
Yes | Add an MVP cache invalidation workflow with no new infrastructure. |
OUTPUT_PATH |
No | docs/cache-refactor-plan.audit.md |
SOURCE_CONTEXT_PATHS |
No | docs/ticket.md,docs/requirements.md |
More from b-mendoza/agent-skills
clarifying-assumptions
Runs the conversational clarification layer for workflow orchestration. Use for plan-wide upfront clarification or task-level pre-execution critique while delegating artifact analysis, manifest assembly, and file updates to bundled subagents.
59recency-guard
Validates answers that depend on current external facts, including prices, versions, policies, rankings, recommendations, documentation, and availability. Use when the user asks for current, latest, verified, fact-checked, or up-to-date answers. Coordinates recency-checker and claim-verifier subagents to produce a current, qualified final answer.
56fetching-jira-ticket
Retrieves a Jira ticket into docs/<TICKET_KEY>.md. Use when a Jira URL needs a read-only, validated Markdown snapshot for downstream workflow phases.
49planning-jira-tasks
Phase 2 of the Jira planning workflow. Reads a Jira ticket snapshot, dispatches a plan/prioritize/validate pipeline, and writes docs/<TICKET_KEY>-tasks.md with branch names for every planned Jira subtask.
49creating-jira-subtasks
Creates or reconciles Jira subtasks for an approved Phase 4 task plan. Use after docs/<TICKET_KEY>-tasks.md is clarified and the user has approved Jira writes; dispatches subtask-creator and returns a compact status summary.
47pr-creator
Create review-ready pull requests from the current branch with a preview-first, user-approved workflow. Use when the user asks to create, open, draft, or submit a PR, pull request, merge request, or code review request, or says their branch is ready for review.
46