requirements-framework-status
This skill should be used when the user asks to "requirements framework status", "show requirements project context", "what's the state of requirements framework", "requirements framework overview", or wants a comprehensive status report of the requirements framework implementation and current state.
What this skill does
# Requirements Framework - Status Report
Provides comprehensive project context and current state of the **Claude Code Requirements Framework**.
## Current Implementation Status
**Version**: 2.5.0
**Status**: ✅ Production Ready & Feature Complete
**Repository**: https://github.com/HarmAalbers/claude-requirements-framework
---
## Quick Metrics
| Metric | Value |
|--------|-------|
| **Production Code** | ~8,500 lines |
| **Test Suite** | 1079 tests (100% pass) |
| **Hooks** | 15 active |
| **Library Modules** | 32 |
| **CLI Commands** | 11 |
| **Requirement Types** | 3 strategies |
| **Plugin Agents** | 25 |
| **Plugin Commands** | 11 |
| **Plugin Skills** | 21 |
**→ Full component inventory**: See `references/component-inventory.md`
---
## Implementation Timeline
### Phase 1: MVP ✅ (2025-12-09)
- Core framework structure
- Session management
- State storage (`.git/requirements/`)
- Configuration cascade
- PreToolUse hook
- CLI tool (`req` command)
### Phase 2: Additional Requirements ⏭️
- Skipped - Not needed for current use cases
### Phase 3: Polish & UX ✅ (2025-12-24)
- Session registry & auto-detection (77 tests)
- Enhanced error messages
- Terminal colors (NO_COLOR support)
- `req init` interactive wizard (42 tests)
- `req config` management (14 tests)
---
## Core Components
### Hooks (15 total)
| Hook | Type | Purpose |
|------|------|---------|
| `check-requirements.py` | PreToolUse | Blocks Edit/Write if unsatisfied |
| `handle-session-start.py` | SessionStart | Context injection, status display |
| `handle-prompt-submit.py` | UserPromptSubmit | Prompt context injection |
| `handle-permission-request.py` | PermissionRequest | Auto-deny dangerous commands |
| `handle-plan-exit.py` | PostToolUse | Show status after planning |
| `auto-satisfy-skills.py` | PostToolUse | Auto-satisfy on skill completion |
| `clear-single-use.py` | PostToolUse | Clear single_use after action |
| `handle-tool-failure.py` | PostToolUseFailure | Failure pattern tracking |
| `handle-subagent-start.py` | SubagentStart | Review agent context injection |
| `handle-pre-compact.py` | PreCompact | Pre-compaction state saving |
| `handle-stop.py` | Stop | Verify requirements before stopping |
| `handle-session-end.py` | SessionEnd | Cleanup sessions |
| `handle-teammate-idle.py` | TeammateIdle | Team progress tracking |
| `handle-task-completed.py` | TaskCompleted | Team task quality gates |
### Libraries (32 modules)
**Core**: `requirements.py`, `config.py`, `state_storage.py`, `session.py`, `registry_client.py`
**Strategies**: `strategy_registry.py`, `base_strategy.py`, `blocking_strategy.py`, `dynamic_strategy.py`, `guard_strategy.py`, `strategy_utils.py`
**Utilities**: `branch_size_calculator.py`, `calculation_cache.py`, `calculator_interface.py`, `message_dedup_cache.py`, `git_utils.py`, `config_utils.py`, `colors.py`, `logger.py`, `feature_selector.py`, `init_presets.py`, `interactive.py`
**Session Learning**: `session_metrics.py`, `learning_updates.py`
**Messages**: `messages.py`, `message_validator.py`
### CLI Commands (11)
`status`, `satisfy`, `clear`, `init`, `config`, `doctor`, `verify`, `sessions`, `list`, `prune`, `logging`
---
## Architecture Overview
### Configuration Cascade
```
Global (~/.claude/requirements.yaml)
↓ (merge if inherit=true)
Project (.claude/requirements.yaml)
↓ (always merge)
Local (.claude/requirements.local.yaml)
```
### Requirement Strategies
| Type | Satisfaction | Use Case |
|------|--------------|----------|
| **Blocking** | Manual (`req satisfy`) | Planning, review |
| **Dynamic** | Auto-calculated | Branch size limits |
| **Guard** | Condition check | Protected branches |
### Session Lifecycle
```
SessionStart → UserPromptSubmit → PreToolUse → PermissionRequest →
PostToolUse → PostToolUseFailure → SubagentStart → PreCompact →
Stop → SessionEnd → TeammateIdle → TaskCompleted
```
**→ Full architecture details**: See `references/architecture-overview.md`
---
## Advanced Features
| Feature | Status | Description |
|---------|--------|-------------|
| Auto-Satisfaction | ✅ | Skills auto-satisfy requirements |
| Single-Use Scope | ✅ | Clears after each action |
| Message Dedup | ✅ | 5-min TTL, 90% spam reduction |
| Stop Verification | ✅ | Blocks stop if unsatisfied |
| Branch Guards | ✅ | Protected branch enforcement |
| Branch Size Calc | ✅ | Dynamic with 30-sec cache |
| Interactive Init | ✅ | 5 context-aware presets |
| Config Management | ✅ | `req config` without YAML editing |
---
## Plugin Components
### Agents (25)
**Workflow**: `adr-guardian`, `codex-review-agent`, `codex-arch-reviewer`, `commit-planner`, `solid-reviewer`, `tdd-validator`
**Review**: `code-reviewer`, `silent-failure-hunter`, `test-analyzer`, `type-design-analyzer`, `comment-analyzer`, `code-simplifier`, `tool-validator`, `backward-compatibility-checker`, `frontend-reviewer`, `refactor-advisor`
**Utility**: `comment-cleaner`, `import-organizer`, `session-analyzer`, `tenant-isolation-auditor`, `appsec-auditor`, `compliance-auditor`
**Refactor Orchestration** (Haiku/Sonnet/Sonnet fanout): `refactor-executor`, `refactor-investigator`, `refactor-analyzer`
### Commands (11)
- `/requirements-framework:arch-review` - Team-based architecture review (recommended for planning)
- `/requirements-framework:deep-review` - Cross-validated team review (recommended for PR)
- `/requirements-framework:pre-commit` - Quick pre-commit review
- `/requirements-framework:codex-review` - Codex-powered review
- `/requirements-framework:commit-checks` - Auto-fix code quality issues
- `/requirements-framework:session-reflect` - Session analysis and improvements
- `/requirements-framework:brainstorm` - Design-first development
- `/requirements-framework:write-plan` - Create implementation plan
- `/requirements-framework:execute-plan` - Execute plan with checkpoints
- `/requirements-framework:refactor-orchestrate` - Multi-layer top-down refactor workflow (produces plan + orchestrator-prompt for fresh-session execution)
### Skills (20)
**Framework Skills (5):**
- `requirements-framework-usage` - Usage help
- `requirements-framework-status` - This skill
- `requirements-framework-development` - Dev workflow
- `requirements-framework-builder` - Extension guidance
- `session-learning` - Session analysis and improvement
**Process Skills (15):**
- `using-requirements-framework` - Bootstrap skill (session start injection)
- `brainstorming` - Design-first exploration
- `writing-plans` - Implementation plan creation
- `executing-plans` - Plan execution with checkpoints
- `test-driven-development` - RED-GREEN-REFACTOR enforcement
- `systematic-debugging` - Root-cause investigation
- `verification-before-completion` - Evidence-based completion
- `subagent-driven-development` - Parallel task execution
- `finishing-a-development-branch` - Branch completion options
- `using-git-worktrees` - Isolated workspaces
- `dispatching-parallel-agents` - Concurrent problem solving
- `receiving-code-review` - Technical feedback evaluation
- `requesting-code-review` - Review agent dispatch
- `writing-skills` - TDD-for-documentation meta-skill
- `refactor-orchestration` - Multi-layer top-down refactor workflow (produces plan + orchestrator-prompt for fresh-session execution)
---
## Architecture Decision Records
| ADR | Decision |
|-----|----------|
| ADR-001 | Remove main/master branch skip |
| ADR-002 | Use Claude Code's native session_id |
| ADR-003 | Dynamic sync file discovery |
| ADR-004 | Guard requirement strategy |
| ADR-005 | Per-project init command |
| ADR-006 | Plugin-based architecture |
| ADR-007 | Deterministic command orchestrators |
| ADR-008 | CLAUDE.md weekly maintenance |
| ADR-009 | Agent auto-fix plan validation |
| ADR-010 | Cross-project feature upgrade |
| ADR-011 | Externalize messages to YAML |
| ADR-012 | Agent Teams integration |
| ADR-013 | Standardized agent output format |
| ADR-014 | Refactor orchestration via bundled skill |
---
#Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.