adlc

Plugin adlc from marketplace adlc-toolkit in atelier-fashion/adlc-toolkit. Commands read from the repo's manifest — 2 days ago.

Skills (17)

• adversary

  Adversarial review of any artifact — a spec, architecture doc, task breakdown, diff/PR, plan, README, or prose claim. Assumes it is wrong, broken, or incomplete, tries to prove it, and reports only the findings that survive its own refutation. Read-only. Use when the user says "attack this", "advers

• analyze

  Codebase health audit — identify technical debt, quality issues, and improvement opportunities

• architect

  Design architecture and break requirement into tasks

• bugfix

  End-to-end bug fix workflow — report, analyze, fix, verify, ship (PR + merge + deploy + knowledge capture)

• canary

  Canary deployment with smoke tests — deploy to a zero-traffic revision, run health checks, and promote on success. Use when the user says "canary deploy", "deploy with canary", "smoke test the deploy", or wants deployment confidence before going live.

• init

  Bootstrap .adlc/ structure in a new repo or subdirectory

• manifest

  Remote-derived view of all in-flight ADLC work — open PRs and pushed feat/REQ-* branches across every session — with a coarse component/domain overlap report. Read-only and advisory.

• optimize

  API cost & performance scanner — identify expensive operations and optimization opportunities

• proceed

  End-to-end ADLC pipeline that takes a requirement from spec through to deployed. Takes a REQ number as argument and runs validate → fix → architect → fix → implement → verify (reflect + review) → create PR → wrapup (merge, deploy, knowledge capture). Use when the user says "proceed", "proceed with R

• reflect

  Post-implementation self-review — catch issues before /review (/adlc:review on the plugin install)

• review

  Multi-agent code review covering correctness, quality, architecture, test coverage, and security

• spec

  Write requirement specs from feature requests

• sprint

  Parallel pipeline orchestrator — launch multiple /proceed sessions concurrently across REQs, monitor progress, and report status. Use when the user says "sprint", "run these REQs in parallel", "proceed with all approved REQs", "launch a sprint", or wants to advance multiple requirements simultaneous

• status

  Show current state of all ADLC work across the project

• template-drift

  Detect drift between the copies `/init` vendored into a project's `.adlc/` (templates, partials, agents, ETHOS, workflow runtime) and the running toolkit install. Use when the user says "check template drift", "template drift", "are my templates out of date", or wants to know whether toolkit templat

• validate

  Validate any ADLC phase output before advancing

• wrapup

  Close out a completed feature — update ADLC artifacts, log knowledge, and summarize

Subagents (19)

• adversary

  Adversarially attacks any artifact (spec, architecture, plan, diff/PR, README, or prose claim) — assumes it is wrong, broken, or incomplete and tries to prove it, then reports only the findings that survive its own refutation attempts. Use as a skeptical-by-default lens; dispatched by /adversary and

• api-cost-scanner

  Scans codebase for AI/API cost optimization opportunities including model usage, token estimates, caching strategies, and redundant calls. Use when auditing API costs.

• architecture-mapper

  Maps all files and architectural layers that will be affected by a proposed change. Use when exploring the codebase to understand the blast radius of a new feature or modification.

• architecture-reviewer

  Reviews code changes for architectural compliance, separation of concerns, test coverage, and API contract adherence. Use when performing code review focused on architecture and testing.

• code-quality-auditor

  Audits codebase for technical debt, dead code, complexity, duplication, and maintenance issues. Use when performing a codebase health audit focused on code quality.

• convention-auditor

  Audits codebase for convention violations including naming, logging, configuration, imports, and error handling patterns. Use when performing a codebase health audit focused on convention compliance.

• correctness-reviewer

  Reviews code changes for logic errors, race conditions, security vulnerabilities, and edge cases. Use when performing code review focused on correctness and bug detection.

• db-perf-scanner

  Scans codebase for database and storage performance issues including Firestore query patterns, GCS operations, pagination, and batching opportunities. Use when auditing database performance.

• delegate-pre-pass

  Per-repo advisory delegation pre-pass for the /sprint --workflow Phase-5 review panel. Runs the gate + worktree diff + redaction + adlc-read I/O and returns a structured CANDIDATES object (untrusted delegate stdout, never acted on). Gated; degrades to an empty-candidates object on any failure and ne

• feature-tracer

  Traces existing features and implementation patterns in the codebase to find similar precedents for a new feature. Use when exploring the codebase during architecture design.

• integration-explorer

  Identifies extension points, existing tests, integration surfaces, and API contracts that a new feature must respect. Use when exploring the codebase to understand integration requirements.

• latency-scanner

  Scans codebase for request latency issues including sequential async operations, payload sizes, middleware overhead, and cold start impact. Use when auditing request performance.

• lite-reviewer

  Single read-only review pass for a lite-lane REQ — covers correctness, quality, architecture, test coverage and security in one pass, marks every numbered BR and AC in the spec met / partial / unmet, and lists any reversal of a recorded decision. Use from /proceed Phase 5 on a lite REQ in place of t

• pipeline-runner

  Runs the complete /proceed pipeline for a single REQ in subagent mode (all phases sequential, no sub-agent dispatch). Use when /sprint needs to run multiple REQs in parallel.

• quality-reviewer

  Reviews code changes for convention compliance, naming standards, code duplication, and quality issues. Use when performing code review focused on code quality and project conventions.

• reflector

  Performs post-implementation self-review using a comprehensive checklist and checks lessons learned for applicable pitfalls. Use for honest self-assessment of recently implemented code before formal review.

• security-auditor

  Audits codebase for security vulnerabilities including input validation, authentication, authorization, data exposure, and dependency issues. Use when performing a security-focused codebase audit.

• task-implementer

  Implements a single ADLC task from a task file, following project conventions and architecture. Use when executing implementation tasks from /proceed Phase 4.

• test-auditor

  Audits codebase for test coverage gaps, mock completeness, test quality, and testing best practices. Use when performing a codebase health audit focused on testing.

Hooks (1)

• SessionStart

  sh "${CLAUDE_PLUGIN_ROOT}/scripts/session-start.sh"