The Agents
Purpose-built AI agents for every phase. Each agent has a specific role, defined capabilities, and clear outputs.
Specialist Agents
Called in when a feature needs deep expertise in a specific area.
Test Specialist
sdlc-testDeep-dive testing for complex features.
Security Specialist
sdlc-securitySecurity review and vulnerability assessment.
Performance Specialist
sdlc-perfPerformance profiling and optimization.
Database Specialist
sdlc-databaseSchema design and query optimization.
Root Cause Analyst
sdlc-root-causeDiagnoses failures and broken behavior. Dual-mode: on-demand diagnosis and Phase 4 failure analysis.
Code Linter
code-linterHybrid linting — runs ESLint/ShellCheck for deterministic checks, then Claude analysis for logic errors and security issues.
Codebase Auditor
codebase-auditorAudits against OWASP Top 10, CWE, SANS/CIS benchmarks, and engineering hygiene frameworks.
Firecrawl Specialist
firecrawlWeb scraping, crawling, and structured data extraction via the Firecrawl API.
Hotfix Agent
sdlc-hotfixStructured bug fix workflow outside the feature SDLC for production issues.
Tech Consultant
tech-consultantPassive pattern enforcer active during all coding, reviewing, and architecture tasks. Prevents over-engineering and ensures existing codebase patterns are followed.
Context Engineer
context-engineeringMeta-skill for managing agent context effectively. Defines context hierarchy, packing strategies, and anti-starvation rules.
Deprecation & Migration
deprecation-and-migrationSafe removal of code, dependencies, and features. Prevents breaking changes from careless removal with Chesterton's Fence principle.
Code Simplification
code-simplificationActive refactoring workflow for simplifying existing code. Rule of 500, structured simplification patterns, and complexity reduction.
Browser Testing
browser-testing-with-devtoolsLive browser inspection via Chrome DevTools MCP — DOM, console, network, performance traces. Treats browser content as untrusted; constrains JavaScript execution.
Source-Driven Development
source-driven-developmentGrounds framework-specific code in official documentation with citations. Detect stack → fetch docs → implement → cite. Prevents stale-training-data drift.
Documentation & ADRs
documentation-and-adrsArchitecture Decision Records and inline documentation patterns. ADR template + lifecycle (Proposed → Accepted → Superseded). Comment the why, not the what.
Stack Watch
stack-watchProactive vendor change monitoring. Discovers your stack from the repo, maintains a diffable STACK.md, then probes vendor changelogs for deprecations, breaking changes, and security advisories. Maps every finding back to the files it touches.
Pipeline Agents
One agent per phase, working in sequence through the pipeline.
Discovery Agent
sdlc-discoverInterviews you about the problem, challenges assumptions, and produces a scoped Problem Brief with clear success criteria.
- Scope definition and constraint setting
- Success criteria extraction
- Risk identification
- Feature sizing (S / M / L)
Architecture Agent
sdlc-architectReads your codebase, analyzes existing patterns, and produces a Technical Design Document that fits what's already there.
- Codebase analysis and pattern detection
- Schema and API design
- Component specification
- Technical Design Document generation
Design Agent
sdlc-designCreates UI/UX specifications for UI-heavy features. Component specs, layout mockups, and interaction patterns.
- Component specification
- Layout and spacing design
- Interaction pattern definition
- Responsive design considerations
Planning Agent
sdlc-planDecomposes the Technical Design Document into ordered, verifiable code prompts with failure recovery strategies.
- Task decomposition
- Dependency ordering
- Verification step definition
- Failure recovery planning
Build Agent
sdlc-buildExecutes code prompts sequentially — writes code, runs checks, handles errors, and commits with conventional messages.
- Code generation and editing
- Automated check execution
- Error recovery and retry
- Conventional commit creation
Compliance Agent
sdlc-complianceValidates code against 23 rules during build and verification. Catches issues before they reach production.
- Code standards enforcement
- Security pattern validation
- API route validation
- Type safety checks
Verification Agent
sdlc-verifyRuns the full QA suite — type checks, lint, tests, security review — and produces a comprehensive QA report.
- Test execution and reporting
- Security audit
- Compliance audit
- QA report generation
Ship Agent
sdlc-shipHandles post-merge deployment verification, updates CLAUDE.md architecture docs, and creates release notes.
- Deployment verification
- CLAUDE.md update
- Release note generation
- Production health check
Retro Agent
sdlc-retroReviews the build cycle, identifies patterns, proposes improvements to skills and process, and tracks tech debt.
- Build cycle analysis
- Pattern identification
- Skill improvement proposals
- Tech debt tracking
Review Subagents v8
Read-only specialists for a second opinion on changed code. Invoked by other agents during verification, or directly by the user.
TypeScript Reviewer
typescript-reviewerSecond-opinion reviewer for TS/Next.js code. Runs tsc --noEmit and lint, then ranks findings BLOCK/WARN/NIT against a stack-specific priority ladder (security → type safety → async → error handling → Next.js → React → style).
Silent Failure Hunter
silent-failure-hunterHunts swallowed errors, floating promises, empty catches, JSON.parse without try/catch, non-Error throws, and similar patterns. Produces numbered findings with severity, impact, and remediation hints. Read-only.
Slash Commands
Operations triggered by typing /name in Claude Code. Grouped by purpose.
SDLC Flow
/new-featureStart a new feature in Phase 0 (Discovery).
/statusPrint current SDLC state — active feature, phase, branch, in-flight items.
/gate-checkVerify the current phase's gate checklist before advancing.
/resume-featureResume work on a previously started feature.
/skip-phaseMark a phase complete without running it. Use sparingly.
/rollbackRevert a feature to a prior phase.
Authoring
/skill-createv8Standardized workflow for authoring new skills — frontmatter, profile registration, CLAUDE.md update.
Session
/checkpointv8Snapshot the current session to .claude/snapshots/checkpoint-<ts>-<label>/ with state, git context, and resume notes.
Git
/prv8Ad-hoc PR creation outside the Phase 5 flow. Title from commits, body from SDLC artifacts.
Lifecycle Hooks v8
Non-blocking Node scripts that fire on Claude Code events. Warnings go to stdout where the agent sees them; never blocks your work. Ships with the full install profile.
session-startPrints active feature, phase, branch, and in-flight features so each session resumes with full SDLC context.
post-edit-formatSilently runs Prettier on edited TS/JS/MD/CSS/JSON files when prettier is available.
post-edit-console-warnWarns when console.log/debug/info appears in production source. Skips test/scripts/config files.
pre-bash-commit-guardBefore any git commit, runs npm run lint + tsc --noEmit and emits a warning if either fails. Never blocks the commit.
pre-compactSnapshots .claude/sdlc-state.json to .claude/snapshots/sdlc-state-<ts>.json before context summarization.
stop-pattern-extractRate-limited (5min) extractor that diffs commits since the last run and appends fix/revert pattern candidates to .claude/snapshots/pattern-candidates.md for Phase 6 retros.