code

Plan Amend - Discuss and apply amendments to a plan.json implementation plan

Cancel active ClosedLoop Loop

!`${CLAUDE_PLUGIN_ROOT}/scripts/setup-closedloop.sh $ARGUMENTS`

Iterative plan refinement debate between Claude and Codex

Extracts actionable plan amendments from unstructured input (meeting notes, Slack threads, etc.)

Processes answered questions from plan.json and incorporates them into relevant tasks.

Produces api-requirements.md from an approved plan. Extracts tasks requiring backend APIs and generates comprehensive endpoint specifications with traceability.

Discovers and runs project validation commands (test, lint, typecheck, build). Caches discoveries as learnings for future runs.

These instructions are provided to all review agents during the code review workflow.

Worker agent for partitioned code review tasks. Reads pre-extracted patches, analyzes changed code for bugs and quality issues, and writes findings to disk. Use when spawning background review agents that need file access.

Reviews code changes for quality, security, and best practices across any language. Use after implementation to identify bugs, security issues, and code quality problems. Returns findings by severity (Critical, High, Medium, Low).

Discovers peer repositories and identifies cross-repo capability needs. Does NOT verify or search peers - that's done by generic-discovery.

Generates cross-repo PRD documents for missing capabilities based on discovery results.

Detects project types and determines how to start dev servers across all workspace repos. Reads .workspace-repos.json for repo list.

Generic cross-repo discovery agent. Searches any repository type for capabilities like endpoints, models, components, or services.

Implements missing requirements for a task from the implementation plan.

Processes pending learnings from $CLOSEDLOOP_WORKDIR/.learnings/pending/ and classifies them for storage

Software architect agent for creating and revising implementation plans. Explores codebases, designs plans, and writes them directly to disk. Used by plan-with-codex for iterative plan refinement.

Creates high-level implementation plan drafts from PRDs. Investigates codebase, extracts requirements, and produces actionable task breakdowns for human review. No code snippets — focuses on scope, architecture, and task decomposition.

Evaluates plan complexity for simple-mode eligibility and selects critic agents

Imports an external markdown plan into the ClosedLoop plan.json format. Reads a source markdown plan, normalizes headings and task lines, derives acceptance criteria, populates all JSON arrays, writes plan.json and plan.md, validates the result, and writes a completion marker.

Validates plan.json structure. Returns format issues, open questions, and pending tasks.

Modifies existing implementation plans — merges critic feedback, finalizes with implementation details, and incorporates addressed gaps. Does not create plans from scratch (use plan-draft-writer for that).

Pre-explores codebase before plan drafting. Produces requirements-extract.json, code-map.json, and investigation-log.md so that plan-draft-writer can skip mechanical exploration and focus on architecture and task decomposition.

Discovers peer repositories for cross-repo orchestration. Uses CLAUDE_WORKSPACE_REPOS env var or sibling directory scanning.

Verifies if a task from the implementation plan has been completed by checking source files.

Performs visual QA inspection using Playwright browser automation.

Skip Phase 7 rebuild when no code changed since Phase 5 build passed. Compares git diff hash against stored hash from last successful build validation. Triggers on: entering Phase 7, checking build status, before final build validation. Returns BUILD_CACHE_HIT to skip or BUILD_CACHE_MISS to re-run build-validator.

Provides ClosedLoop environment paths (CLOSEDLOOP_WORKDIR, CLAUDE_PLUGIN_ROOT) to agents. This skill should be used by any agent that needs to access ClosedLoop run directories, plugin schemas, or other path-dependent resources.

Run Codex to review a plan file and return structured feedback with a verdict. Triggers on: debate loop Codex review rounds. Returns VERDICT:APPROVED or VERDICT:NEEDS_CHANGES plus CODEX_SESSION token.

Check if critic reviews are still valid before re-running Phase 2.5 critics. Compares plan.json + critic-gates.json content hash against stored hash from last critic run. Triggers on: entering Phase 2.5, checking critic cache, before launching critics. Returns CRITIC_CACHE_HIT to skip critics or CRITIC_CACHE_MISS to re-run them.

Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches. Compares peer repo git hashes against stored hashes from last coordinator run. Triggers on: entering Phase 1.4.1, checking cross-repo cache, before discovering peers. Returns CROSS_REPO_CACHE_HIT with cached status or CROSS_REPO_CACHE_MISS to re-run coordinator.

Sync plan.md with plan.json content. MUST be used after ANY edit to plan.json to keep plan.md in sync. Triggers: - After editing plan.json with Edit tool (REQUIRED - always sync after edits) - User asks to "sync plan.md", "update plan.md", "extract the md from a plan" - Converting plan.json to markdown or viewing plan as standalone markdown IMPORTANT: Whenever plan.json is modified, plan.md must be updated to match.

This skill should be used when needing to locate files within the Claude Code plugins cache directory (~/.claude/plugins/cache). Triggers include finding tool scripts, skill files, or any plugin resource when the hardcoded path is unknown or varies by plugin version. Use when slash commands or orchestrators need to dynamically resolve plugin file paths.

Protocol for iteratively refining sub-agent queries through follow-up questions to ensure sufficient context

Conventions for editing plan.json implementation plans including task format, structured arrays, and plan structure rules. Use when creating or modifying plan.json files.

Used when creating or updating implementation plans.

Deterministic plan.json validation via Python script, replacing most plan-validator agent calls. Performs JSON parsing, schema validation, task checkbox regex, required section checks, sync validation, and data extraction. Only semantic consistency checks (storage/query alignment) require the LLM agent. Triggers on: plan validation, checking plan format, extracting plan data. Returns PLAN_VALID with extracted data or PLAN_FORMAT_ISSUES with issues list.

This skill helps PMs draft lightweight PRDs. It should be used when a PM wants to define a new feature, brainstorm requirements, or prep for sprint planning. Triggers include "I have a feature idea", "help me write a PRD", "let's break this into stories", or "what do I need for sprint planning". Optimized for speed — generates minimal viable documentation through conversation, not heavy templates.

6 hooks across 5 events