Search everything...

Stats

Actions

Available In

agents-core

Name: agents-core
Author: forgeplan

By ForgePlan

v1.4.1: coder body gains a 'TDD GREEN-phase discipline' section (RFC-012 FR-4) — when dispatched in a TDD GREEN phase, never Write/Edit test files; on a wrong test STOP and emit TEST_BUG; lint after each change. v1.4.0: code-reviewer + tester (Profile B) bodies gain Step 4.5 Ground-truth verification clause (RFC-011 FR-3) — reviewers MUST read frozen git diff themselves before PASS; empty diff on a claimed change = BLOCKER (vacuous green). Core development agents: debugger, code reviewer, error detective, performance engineer, production validator, plus a complete dev team (coder, planner, researcher, reviewer, tester, TDD London School). v1.3.1: code-reviewer + tester (Profile B) bodies patched with Step 9b NEEDS_ACTIVATION sentinel emit instruction per Sprint E PRD-033 — Profile B reviewers now emit `<<NEEDS_ACTIVATION: EVID-XXX>>` on first line of return to enable orchestrator auto-activation. v1.3: 8 legacy specialists canonical-lint compliant. v1.2: coder Profile C-coder + code-reviewer + tester (batch 2 forgeplan-aware migration).

npx claudepluginhub forgeplan/marketplace --plugin agents-core

Popularity

Stars

Above avg

Med: 0·Avg: 363

Installs

Med: 0·Avg: 2

What's Inside

Agents11

code-reviewer

/code-reviewer

Methodology: CRUD-R-A Profile B (code review → EVIDENCE w/ PASS/CONCERNS/BLOCKER + STRIDE/OWASP findings). EN: Code reviewer. Reads a diff (or specified file set), runs lint/type-check/tests via Bash, and produces a forgeplan EVIDENCE artifact with verdict (PASS / CONCERNS / BLOCKER) plus categorised findings (Bug / Style / Architecture / Performance / Docs / Test gap). Reports issues with `file:line` references — does **not** rewrite code. When fixes are needed, the orchestrator dispatches a Profile C-coder agent. Tags every claim/release with its identity for audit trail. RU: Ревьюер кода. Читает diff (или указанный набор файлов), запускает lint/type-check/тесты через Bash и создаёт forgeplan EVIDENCE artifact с verdict (PASS / CONCERNS / BLOCKER) и категоризированными findings (Bug / Style / Architecture / Performance / Docs / Test gap). Сообщает об issues со ссылками `file:line` — код сам **не** правит. Когда нужны фиксы, оркестратор диспатчит Profile C-coder агента. Метит каждый claim/release своей identity для audit trail. Triggers: "review this PR", "code review", "review the diff", "ревью кода", "проверь PR", "audit changes", "review for bugs", "ревью diff", "проверь изменения", "review changes before merge", "pre-merge review"

coder

/coder

Methodology: CRUD-R-A Profile C-coder (source-mutating implementation only). EN: Source-mutating implementation agent (Profile C-coder). The only agent allowed to use Write / Edit / Bash on source files. Reads the parent RFC / SPEC via forgeplan MCP, writes the code, runs local compile / lint / typecheck, and hands off to a Profile B reviewer (code-reviewer / tester / security-expert) for EVIDENCE recording. Never creates, mutates, or links forgeplan artifacts — the whitelist physically forbids forgeplan_new / update / link. Never decides artifact lifecycle. RU: Агент-исполнитель, мутирующий исходники (Profile C-coder). Единственный агент, которому разрешены Write / Edit / Bash на source files. Читает родительский RFC / SPEC через forgeplan MCP, пишет код, запускает локально compile / lint / typecheck и передаёт Profile B рецензенту (code-reviewer / tester / security-expert) для записи EVIDENCE. Никогда не создаёт, не мутирует и не линкует forgeplan artifacts — whitelist физически запрещает forgeplan_new / update / link. Никогда не решает lifecycle артефактов. Triggers: "implement", "write code", "build it", "make it work", "реализуй", "напиши код", "code this up", "программируй", "implement the RFC", "apply this refactor", "fix this bug per SPEC"

debugger

/debugger

EN: Expert debugger specializing in complex issue diagnosis, root cause analysis, and systematic problem-solving across multiple languages and environments. Use when a bug resists quick fixes, requires bisection / differential analysis, or spans memory, concurrency, or production boundaries. Hand off to `error-detective` for cascade mapping, or to `tester` (Profile B) after a fix is confirmed. RU: Эксперт-отладчик, специализирующийся на диагностике сложных проблем, анализе первопричин и систематическом решении задач в нескольких языках и окружениях. Используйте когда баг не поддаётся быстрым исправлениям, требует бисекции / дифференциального анализа или затрагивает память, параллелизм или production-границы. Передайте `error-detective` для каскадного анализа или `tester` (Profile B) после подтверждения исправления. Triggers: "debug", "root cause", "bug investigation", "bisect", "race condition", "memory leak", "breakpoint", "stack trace", "отладка", "первопричина", "расследование бага", "утечка памяти"

error-detective

/error-detective

EN: Forensic error investigator performing root cause analysis, cascade failure mapping, log correlation, and anomaly detection across distributed and monolithic systems. Use when an incident involves multiple services, unclear blast radius, or requires timeline reconstruction from logs. Hand off to `debugger` for code-level fixes, or to `performance-engineer` if the root cause is a bottleneck. RU: Криминалист-следователь ошибок, выполняющий анализ первопричин, картирование каскадных сбоев, корреляцию логов и обнаружение аномалий в распределённых и монолитных системах. Используйте когда инцидент охватывает несколько сервисов, blast radius неясен, или требуется реконструкция хронологии по логам. Передайте `debugger` для исправления на уровне кода или `performance-engineer` если первопричина — узкое место. Triggers: "error investigation", "cascade failure", "log correlation", "incident analysis", "blast radius", "root cause analysis", "distributed failure", "расследование ошибок", "каскадный сбой", "корреляция логов", "анализ инцидента"

performance-engineer

/performance-engineer

EN: Senior performance engineer covering end-to-end profiling, bottleneck analysis, optimization techniques (caching, query tuning, parallelization), monitoring, SLA management, and capacity planning. Use when latency or throughput targets are missed, after a load test exposes regressions, or when scaling decisions need data. Hand off findings to `coder` for implementation or to `production-validator` before release. RU: Старший инженер по производительности, охватывающий сквозное профилирование, анализ узких мест, техники оптимизации (кэширование, настройка запросов, параллелизм), мониторинг, управление SLA и планирование мощностей. Используйте когда цели по задержке или пропускной способности не достигаются, после нагрузочного теста обнаруживающего регрессии, или когда решения по масштабированию требуют данных. Передайте `coder` для реализации или `production-validator` перед релизом. Triggers: "performance analysis", "profiling", "bottleneck", "latency", "throughput", "SLA", "capacity planning", "N+1", "cache hit rate", "анализ производительности", "профилирование", "узкое место", "задержка"

README

English | Русский

ForgePlan — From Raw Idea To Proven Decision

ForgePlan Marketplace

Official plugin marketplace for Claude Code from ForgePlan — UX, workflow, engineering, and developer tools.

18 plugins | 25 marketplace-aware agents (75 total) | 38+ skills | 9+ knowledge bases

ForgePlan ecosystem: this marketplace + forgeplan CLI (artifact lifecycle) + @forgeplan/web (browser viewer with time-travel + graph). Three siblings; install what you need.

📚 Documentation

Guide	When to read
👋 Onboarding	Read this first — pocket guide, friendly tone, get from zero to autonomous agent dispatch in 30-60 min. Hindsight setup + command cookbook + when-you're-needed matrix
🚧 Brownfield guide	Companion to Onboarding — existing codebases, Discover Agent, Strangler Fig + DDD + ACL with concrete examples
🚀 Developer Journey	Longer 30-min walkthrough from zero to your first shipped feature, with 4 persona Day 0 walkthroughs
🧭 Smith — master orchestrator	Routing map: 12 contexts × 27 methodologies. When and how to dispatch `/smith` as the BMAD-style master that picks the right workflow for the task
📋 Playbook	Use-case matrix: which command for which scenario (empty project, brownfield, night-run, …)
📖 Usage Guide	Reference manual: 18 commands, hooks, agent activation rules, troubleshooting
🏛 Architecture	4-layer mental model — Orchestra (where) · Forgeplan (what) · FPF (how to think) · SPARC (how to code)
🔬 Methodologies	What's built into forgeplan (BMAD, OpenSpec, ADI, F-G-R, DDR, Verification Gate) vs what's external
🔁 Autoresearch integration	Combining `uditgoenka/autoresearch` (metric-driven loops) with `/forge-cycle` lifecycle
🧭 AI-SDLC mapping	Phase-by-phase map for users coming from AI-SDLC vocabulary (Concept → Research → Design → Build → Test → Release → Operate → Maintain)
📚 Upstream methodologies	Bibliography — pointers to Quint-code, BMAD, OpenSpec, FPF, Karpathy autoresearch, git-adr, ccpm, adr-tools
🛠 Setup Guide for new repo	End-to-end bootstrap (~20 min): forgeplan + Claude Code plugins + GitHub Projects v2 + auto-add workflow + convention. Use when adding a new ForgePlan repo to the ecosystem.
🚚 Migration: dev-toolkit → fpl-skills	Switching plugins safely (side-by-side or clean-cut, with rollback plan)
🗂 Tracker Integration	Recipes for Orchestra · GitHub Issues · Linear · Jira · local TODO
🌐 Forgeplan Web	Browser viewer — time-travel slider + artifact graph + health dashboard
🔄 Process Reference (EN) / RU	Full process from idea to commit — 5 agent profiles, 10 artifact kinds, 4-layer pipeline, methodologies (BMAD/FPF/SPARC/RIPER-5)
📜 Changelog	Release history
🤝 Contributing	Add a new plugin to the marketplace

Quick Start

# 1. Add the ForgePlan marketplace
/plugin marketplace add ForgePlan/marketplace

# 2. Install your first plugin (works with any project, no dependencies)
/plugin install dev-toolkit@ForgePlan-marketplace

# 3. Reload to activate
/reload-plugins

# 4. Try it — run a code audit
/audit

Where to Start?

New here? Pick the row that matches you. Each row is a complete setup — no need to read the full catalog.

Your role	Install these	Why
I want a master orchestrator	fpl-skills + agents-pro	Start here → `/smith` routes 12 contexts to 27 methodologies
Forgeplan user (recommended)	fpl-skills	One install, 38 skills, full route → ship loop
Any developer (no forgeplan)	dev-toolkit + agents-core	Universal tools, no CLI dependency
Frontend	fpl-skills + laws-of-ux + agents-domain	UX + framework agents
Architect	fpl-skills + fpf + agents-pro + agents-sparc	Thinking + SPARC
Multi-session / team	fpl-skills + forgeplan-orchestra	Coordination + Inbox Pattern
Brownfield migration	fpl-skills + forgeplan-brownfield-pack	Ingest legacy docs + C4/DDD/research analyses
Everything	All 18 plugins	Complete ecosystem

Available Plugins

fpl-skills

View full README on GitHub

Similar Plugins

fullstack-dev-skills

10.0k·616·

Comprehensive 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.

1mo

v0.4.15

Jeffallan

feature-dev

30.6k·172·

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

4mo

v1.0.0

anthropics

godot-skills

30·436·

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.

5mo

v1.0.0

Randroids-Dojo

pr-review-toolkit

30.2k·292·

Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification

2mo

v1.0.0

anthropics

ponytail

72.7k·1.1K·

Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.

v4.8.4

DietrichGebert

nature-skills

20.0k·337·

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.

v1.0.0

Yuan1z0825

More by ForgePlan

fpl-hsmem

2·

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).

v2.1.0

ForgePlan

fp-cookbook

2·

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.

v1.2.1

ForgePlan

laws-of-ux

2·

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).

v1.4.1

ForgePlan

fpf

2·

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).

v1.4.1

ForgePlan

forgeplan-orchestra

2·

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).

v1.4.1

ForgePlan

agents-core

Popularity

Confidence

What's Inside

README