By ForgePlan
v1.3.2: ADR-012 internal codename rendered hook-gate (was a Russian codename) in shipped artifacts — sparc-orchestrator + /sparc skill; terminology only, no behavior change. v1.3.1: /sparc skill Step 2 reframed - hook-gate=No means the MAIN SESSION orchestrates the walk (dispatches phase agents directly); a dispatched sparc-orchestrator subagent cannot nest-dispatch (it is a planner/guardrail, not an executor) - per the RFC-016 live dogfood (EVID-165). SPARC development methodology agents: orchestrator with quality gates, plus 4 phase specialists (specification, pseudocode, architecture, refinement/TDD). v1.3.0: THIRD instance of the AD/AID-PDLC sub-cycle contract (ADR-010 / RFC-016) — sparc-orchestrator finished to a contract-conformant Profile B-orchestrator (disallowedTools denylist + Task-dispatch + C1-C6 framing; closes the LR-8 tools allowlist / EVID-153 F2) + NEW /sparc skill (5-phase master-coordinated walk: Specification→Pseudocode→Architecture→Refinement→Completion, mandatory per-gate independent C4, Pseudocode-absorption, Refinement→TDD delegation). hook-gate=No — no hook, no lib, no init. v1.2.2: refinement notes enforced-TDD delegation (RFC-012) — RED test-writing delegates to agents-tdd:coder-tdd and GREEN to agents-core:coder; refinement retains refactor-after-green. v1.2: ALL 5 agents canonical-lint compliant — sparc-orchestrator + pseudocode + refinement migrated to model=opus|sonnet, hex colors, bilingual EN/RU/Triggers descriptions (legacy lint warnings eliminated). 100% of agents-sparc pack passes LR-1..LR-3. specification + architecture remain forgeplan-aware Profile A (PRD-026 Phase 3 batch 1).
Methodology: SPARC Architecture phase + CRUD-R-A Profile A (RFC creation w/ module breakdown, FPF ADI for option selection). EN: SPARC Architecture phase specialist. Transforms a parent PRD or SPEC into a concrete RFC artifact — module breakdown, component contracts, data flow, function signatures, trade-offs, risks, and test hooks. Creates, links, and validates the RFC via forgeplan MCP — never writes files directly. Calls FPF ADI reasoning before picking a design option and weighs at least two genuinely considered alternatives. Tags every claim with its identity for the audit trail. RU: Специалист по фазе Architecture в SPARC. Превращает родительский PRD или SPEC в конкретный RFC — декомпозиция модулей, контракты компонентов, поток данных, сигнатуры функций, trade-offs, риски и хуки для тестирования. Создаёт, связывает и валидирует RFC через forgeplan MCP — никогда не пишет файлы напрямую. Запускает FPF ADI reasoning до выбора варианта дизайна и взвешивает минимум два альтернативных варианта. Метит каждый claim своей identity для audit trail. Triggers: "design the architecture", "create RFC", "module breakdown", "system design", "architecture phase", "архитектурный план", "создай RFC", "разбей на модули", "SPARC architecture"
EN: SPARC Pseudocode phase specialist. Takes a parent SPEC/PRD or RFC draft and produces algorithm sketches, data structure choices, and complexity analysis (Big-O for time + space) BEFORE any code is written. Bridges Specification → Architecture by validating that the algorithmic core fits the constraints. Not forgeplan-aware — operates on local pseudo-code files. Hand off to `architecture` for concrete RFC, then to `coder` (C-coder profile) for implementation. RU: Специалист фазы SPARC Pseudocode. Берёт родительский SPEC/PRD или черновик RFC и выдаёт скетчи алгоритмов, выбор структур данных и анализ сложности (Big-O для времени и памяти) ДО написания кода. Мост между Specification → Architecture: проверяет, что алгоритмическое ядро влезает в ограничения. Не forgeplan-aware — работает с локальными pseudo-code файлами. Передаёт `architecture` для конкретного RFC, далее `coder` (Profile C-coder) для реализации. Triggers: "pseudocode", "algorithm design", "complexity analysis", "Big-O", "data structure choice", "SPARC pseudocode phase", "псевдокод", "анализ сложности", "выбор алгоритма", "выбор структуры данных", "before implementation sketch"
EN: SPARC Refinement phase specialist. Executes red-green-refactor TDD loop on a code surface produced by `coder`: writes failing test (red), implements minimal change to pass (green), refactors for clarity/performance (refactor). Also handles post-implementation polish — error handling, edge cases, performance tuning. Operates on source files only; not forgeplan-aware. Hand off to `tester` (Profile B) for coverage delta EVIDENCE recording. RU: Специалист фазы SPARC Refinement. Прогоняет цикл red-green-refactor TDD на код-поверхности от `coder`: пишет падающий тест (red), реализует минимальное изменение для прохождения (green), рефакторит для ясности/производительности (refactor). Также post-implementation polish — error handling, edge cases, performance tuning. Работает только с source files; не forgeplan-aware. Передаёт `tester` (Profile B) для записи coverage delta в EVIDENCE. Triggers: "TDD refinement", "red green refactor", "refactor this code", "improve test coverage", "tune performance", "SPARC refinement", "TDD", "tighten the implementation", "уточни реализацию", "TDD цикл", "рефакторинг", "оптимизация производительности"
Methodology: SPARC methodology master (Profile B-orchestrator) — the L2 stage-master of the SPARC feature sub-cycle, the THIRD instance of the AD/AID-PDLC sub-cycle contract (ADR-010, contract C1-C6; RFC-016). Peer of smith, bmad-orchestrator, and tdd-orchestrator. Unlike TDD (a single Build-stage sub-cycle) and BMAD (the whole greenfield arc), SPARC drives a SINGLE feature in an EXISTING active system through five phases — Specification → Pseudocode → Architecture → Refinement → Completion — coordinating via Task with a blocking generator≠verifier gate at every phase; never writes code, tests, or artifacts itself; never activates. EN: Master orchestrator for the SPARC feature pipeline. Reads the feature context (an active parent PRD / a feature brief on an active codebase), then walks the five phases as separate isolated-context dispatches via Task — specification (Spec→PRD/SPEC) → pseudocode (algorithm notes) → adr-architect+architecture (Arch→RFC[+ADR]) → refinement+coder (Refine→code+tests, optionally delegating to the TDD sub-cycle) → evidence-recorder (Completion retro) — with a BLOCKING quality-gate between every phase and MANDATORY independent C4 validations at each gate (artifact-reviewer/architect-reviewer on the spec, architect-reviewer on the RFC, tester+code-reviewer on the code). hook-gate=No: there is NO fail-closed hook — C5 is harness phase-ordering (no source/test dispatch until the Architecture RFC is active) + delegating Refinement to the existing TDD hook-gate (RFC-012) when test-immutability matters. Refuses to start without an active parent context (precondition C1). NEVER writes source/test/artifact files; NEVER calls forgeplan_activate. Cite ADR-010 contract C1-C6 + RFC-016. RU: Мастер-оркестратор SPARC feature pipeline. Читает контекст фичи (активный родительский PRD / бриф фичи на активной кодовой базе), затем ведёт пять фаз отдельными изолированными контекстами через Task — specification (Spec→PRD/SPEC) → pseudocode (алгоритм-заметки) → adr-architect+architecture (Arch→RFC[+ADR]) → refinement+coder (Refine→код+тесты, опц. делегируя в TDD-подцикл) → evidence-recorder (Completion retro) — с БЛОКИРУЮЩИМ quality-gate между каждой фазой и ОБЯЗАТЕЛЬНЫМИ независимыми C4-валидациями на каждом гейте (artifact-reviewer/architect-reviewer на спеке, architect-reviewer на RFC, tester+code-reviewer на коде). hook-gate=No: НЕТ fail-closed хука — C5 это harness phase-ordering (не диспатчить source/test, пока Architecture RFC не active) + делегирование Refinement в существующий TDD hook-gate (RFC-012). Отказывается стартовать без активного родительского контекста (precondition C1). НИКОГДА не пишет source/test/artifact файлы; НИКОГДА не вызывает forgeplan_activate. Цитирует ADR-010 contract C1-C6 + RFC-016. Triggers: "SPARC orchestration", "SPARC pipeline", "guide through SPARC", "five-phase delivery", "SPARC quality gates", "structured delegation", "SPARC methodology", "feature in existing system", "spec to completion", "single feature pipeline", "проведи через SPARC", "SPARC оркестрация", "координируй пять фаз", "фича в существующей системе", "spec pseudo arch refine complete"
Methodology: SPARC Specification phase + CRUD-R-A Profile A (PRD/SPEC creation with SMART AC). EN: SPARC Specification phase specialist. Produces forgeplan PRD or SPEC artifacts via MCP — requirements, constraints, SMART acceptance criteria, out-of-scope. Never writes files directly. Calls forgeplan_reason before finalising acceptance criteria. Tags every claim with its identity for audit trail. RU: Специалист фазы SPARC Specification. Создаёт PRD или SPEC артефакты через forgeplan MCP — требования, ограничения, SMART acceptance criteria, out-of-scope. Никогда не пишет файлы напрямую. Запускает forgeplan_reason до фиксации acceptance criteria. Метит каждый claim своей identity для audit trail. Triggers: "write spec", "create PRD", "specification phase", "define requirements", "acceptance criteria", "опиши требования", "создай PRD", "опиши спецификацию", "user story", "SPARC specification"
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimUses power tools
Uses Bash, Write, or Edit tools
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
ForgePlan Hindsight memory plugin for Claude Code. Long-term cross-session memory wrapping Hindsight (vectorize-io). Provides 13 MCP tools (memory_* + mental_model_* + document_ingest_*), 3 auto-hooks (recall on UserPromptSubmit, retain on Stop, force-retain on SessionEnd), and 5 helper skills (/status, /bootstrap, /mental-model, /diagnose, /export-bank). Three activation modes: plugin install (default-on, bank derived from cwd), per-project setup CLI (explicit `.mcp.json`), or direct MCP wire-up (standalone bundle). Source code colocated under plugins/fpl-hsmem/src/. Implements Ruflo-style outcome-feedback patterns (NOTE-004).
Practical cookbook of forgeplan CLI recipes — task-oriented how-to guides covering getting-started, PRD authoring, Evidence patterns, workflow cycles, multi-plugin discipline, AI-pair dispatch, troubleshooting Sprint A-O anomalies, and CLI/MCP quick-reference. Each recipe: Цель → Команда → Пример → Common errors. / Практическая поваренная книга рецептов forgeplan CLI — пошаговые руководства по онбордингу, PRD, Evidence, рабочим циклам, мультиплагинной дисциплине, диспетчеризации AI-агентов, устранению аномалий и справочнику CLI/MCP.
UX laws knowledge base and frontend code reviewer. Analyzes HTML/CSS/JS/React/Vue/Svelte code against 30 Laws of UX principles. Provides actionable recommendations for improving user experience. Use when building UI components, reviewing frontend code, or learning UX best practices. v1.4.1: ux-reviewer agent canonical-lint compliant (LR-1..LR-3).
First Principles Framework (FPF) — thinking amplifier for structured reasoning, system decomposition, and decision-making. Enhanced version with applied patterns, forgeplan integration, and practical commands. Based on the FPF specification by Anatoly Levenchuk. v1.4.1: fpf-advisor agent canonical-lint compliant (LR-1..LR-3).
Unified workflow: Forgeplan artifacts + Orchestra task tracking + Claude Code AI execution. Bidirectional sync, Session Start Protocol with Inbox Pattern, and methodology knowledge base. Requires forgeplan CLI (private app, access via project admin) + Orchestra MCP server. v1.4.1: orchestra-advisor agent canonical-lint compliant (LR-1..LR-3).
npx claudepluginhub forgeplan/marketplace --plugin agents-sparcComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Harness-native ECC plugin for engineering teams - 67 agents, 277 skills, 93 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.