Flagship workflow plugin of the ForgePlan ecosystem — the skills, templates and authoring contract the rest of the marketplace is written against: the smith methodology router (14 contexts), the agent-authoring guide every forgeplan-aware agent follows, and the gate, cleanup and insight skills that keep a pipeline honest. Use when you want the methodology itself rather than one specialist — deciding how to approach a task, gating an artifact before activation, or authoring a new agent to the house canon. Full history in CHANGELOG.md.
44 skills · 1 agent · hooks
Professional specialist agents: security and prompt-injection review, PII detection, architecture and staff-level system review, the pre-activation guardian gate, ADR and specification authors, research analysts and infrastructure roles. Use when a task needs a named expert rather than a generalist — an OWASP/STRIDE pass, an architectural fitness review, a decision recorded as an ADR, or the last gate before an artifact is activated. Full history in CHANGELOG.md.
30 agents
CANVAS design-system-to-code methodology: a coordinator walks a Pencil design through capture, audit, norm-check, vectorize and assemble, dispatching every phase and every verifier as a separate isolated context with a blocking generator-is-not-verifier gate at each handoff, plus a fail-closed hook that blocks source writes until the token contract is active. Use when a design system has to become working components in the project's own framework, with visual parity and token fidelity proven rather than asserted. Full history in CHANGELOG.md.
6 skills · 4 commands · 8 agents · hooks
Builds a navigable map of a project — zones, nodes and verified edges — as a `map.json`, through an eight-agent pipeline (scan -> extract -> verify -> emit -> validate) where every stage runs in a fresh isolated context and a deterministic guardian script, not an LLM, is the sole authority on whether the result can be trusted. Use when you need a structural view of a large or unfamiliar repository that a file tree cannot give, or when a project's forgeplan artifact graph should be shown alongside its code. Not a documentation generator: an edge is either sourced from the artifact graph or proven by a grep, and an unproven one is dropped rather than shipped as noise. Full history in CHANGELOG.md.
3 skills · 4 commands · 8 agents · hooks
Project-scoped cross-session memory for Hindsight API >=0.10.2 and <0.11.0. Use when a repository explicitly opts in via .hindsight.json; hooks default off, enrichment is operator-gated, and BankGate is client safety, not server authorization.
10 skills · 1 agent · 1 MCP server · hooks
Brownfield extraction pack — turns legacy code and documents into a structured forgeplan graph through a discover agent and twelve extraction skills (ubiquitous language, use cases, invariants, causal links, scenarios, knowledge-graph curation, reproducibility). Use when taking over an undocumented codebase and the first problem is not what to build but what is already there and why it is that way. Full history in CHANGELOG.md.
12 skills
Core engineering agents: the source-mutating coder, the code reviewer and test runner that record evidence, plus debugger, planner, researcher, performance and production-readiness roles. Use when the work is ordinary engineering — implement this, review that diff, run the suite and report coverage against the acceptance criteria — and the reviewer should be a different context from the author. Full history in CHANGELOG.md.
11 agents
Domain specialist agents for languages and frameworks: TypeScript, Go, React, Next.js, Electron, embedded systems, fullstack, game development, mobile and WebSocket engineering. Deliberately not forgeplan-aware — they advise on code, not on the artifact graph. Use when the question is idiomatic within one stack, where a generalist answers plausibly but not idiomatically. Full history in CHANGELOG.md.
11 agents
Runs one tracked task end to end on whatever issue tracker a project uses — Orchestra, Jira, Linear, GitHub Issues — through seven gated stages, and carries the Orchestra MCP reference (field model, failure modes, query recipes) as a separate skill free of this ecosystem. Use when the board should tell the truth about work in flight: picking a task that can actually be started, keeping its checklist honest while the work happens, proving each acceptance line, and reporting what was NOT done alongside what was. Full history in CHANGELOG.md.
3 skills · 2 commands · 2 agents · hooks
GitHub operations agents: pull-request lifecycle, issue triage, release automation, multi-repository coordination, project boards, workflow engineering and repository scaffolding. Deliberately not forgeplan-aware — these operate on GitHub, not on the artifact graph. Use when the work is GitHub itself: opening a PR with a real checklist, finding what is blocked on CI, cutting a release, or propagating one change across many repositories. Full history in CHANGELOG.md.
7 agents
Enforced test-driven development: an orchestrator drives plan -> failing tests -> independent validation -> implementation, with a fail-closed hook that blocks source writes until the tests exist, and a separate context that certifies the RED is real before GREEN may start. Use when a spec carries concrete scenarios and the tests should be the oracle rather than an afterthought — the validator exists because a test written by the same context that writes the code is not a check. Full history in CHANGELOG.md.
2 skills · 4 agents · hooks
[DEPRECATED — superseded by fpl-skills] Universal engineering toolkit: multi-expert audit, wave-based sprints, session context recall, structured reports with auto-trigger hooks, and safety hooks. Works with any project and language. Use only if you already depend on it — new users should install fpl-skills instead, which supersedes it. Full history in CHANGELOG.md.
1 skill · 4 commands · 1 agent · hooks
First Principles Framework — a thinking amplifier for structured reasoning, system decomposition and decision-making, with applied patterns, forgeplan integration and practical commands. Based on the FPF specification by Anatoly Levenchuk. Use when a decision needs more than an opinion: generating genuine alternatives before choosing one, decomposing a system into bounded contexts, or scoring the evidence instead of asserting it. Full history in CHANGELOG.md.
1 skill · 5 commands · 1 agent
Slopocop communication layer for clear development replies, plus targeted RU/EN prose editing across agents. Three skills: slopocop for concise, technically precise replies, questions and progress; humanizer-ru for Russian text; slop-humanizer for English text or requested prose. Use when improving agent communication, humanizing text or auditing prose. Adds to existing instructions through Claude Code hooks, trusted Codex hooks, an OMP extension or a host-neutral startup-instruction installer. Editorial commands and the slop-cop reviewer remain Claude-native. No per-reply editor, evaluator or runtime network downloads.
3 skills · 2 commands · 1 agent · hooks
SPARC methodology agents — specification, pseudocode, architecture, refinement, and the orchestrator that walks a single feature through all five phases with a blocking quality gate between each. Use when adding one feature to an existing, active system and the design should be settled before code: the middle path between greenfield BMAD and a tactical fix. Full history in CHANGELOG.md.
1 skill · 5 agents
Slop cop for design — stops UI from looking AI-generated. The design counterpart to slopocop (text). Ships hallmark (anti-AI-slop design engine: 58-gate slop-test, 21 macrostructures, 50 components, audit/redesign/study) plus two taste skills (frontend-design by Anthropic, design-taste-frontend), two commands (/design-audit ranked slop findings with no edits, /design-redesign a fresh visual take that preserves routes/copy/logic), and an on-demand design-cop reviewer agent. No hook by design — laws-of-ux already nudges on frontend edits. Use when building or redesigning a page, or auditing UI for templated slop. Text slop lives in slopocop. v1.1.0: Каждый агент пакета получил секцию `## Model tier`: какой ЯРУС нужен его работе и почему ярус задаёт самая трудная стадия, а не самая частая. Там же сказано, что значение `model:` во фронтматтере — привязка Claude Code, а не требование: в OMP/OpenCode/Codex/Gemini этих имён нет, надо подставить модель своего яруса и при промахе промахиваться ВВЕРХ. Лестница ярусов — `docs/GUIDE-AI-SDLC-PDLC-RU.md` §6.2, здесь она не пересказывается.
3 skills · 2 commands · 1 agent
Structured engineering workflow for forgeplan users: `/forge-cycle` drives one artifact through the full pipeline to activation with the quality gates enforced at each stage, and `/forge-audit` reviews what came out. Use when a piece of work is Standard depth or above and should not reach activation without evidence, a review and a gate — the cycle refuses to advance rather than letting a stage be skipped quietly. Full history in CHANGELOG.md.
1 skill · 2 commands · 1 agent · hooks
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). v1.6.0: Каждый агент пакета получил секцию `## Model tier`: какой ЯРУС нужен его работе и почему ярус задаёт самая трудная стадия, а не самая частая. Там же сказано, что значение `model:` во фронтматтере — привязка Claude Code, а не требование: в OMP/OpenCode/Codex/Gemini этих имён нет, надо подставить модель своего яруса и при промахе промахиваться ВВЕРХ. Лестница ярусов — `docs/GUIDE-AI-SDLC-PDLC-RU.md` §6.2, здесь она не пересказывается.
1 skill · 2 commands · 1 agent · hooks
BMAD greenfield methodology: a master orchestrator walks the persona arc — Analyst, PM, Architect, Scrum-Master, Dev, QA — as separate isolated contexts, with a blocking quality gate between every persona and a fail-closed no-code-before-plan hook. Use when building a new product or service from nothing; not for one feature in an existing system (that is SPARC), and not for modernising legacy (that is Strangler Fig). Full history in CHANGELOG.md.
2 skills · 1 agent · hooks
Slop cop for code — finds and strips the AI-authorship fingerprint in source without changing behaviour: redundant comments, defensive bloat, one-implementation abstractions, generic naming, banner comments, copy-paste blocks. Ships a deterministic 0-100 scanner across seven languages, dependency-free. Use before a review or a merge when code was AI-drafted and reads like it. Full history in CHANGELOG.md.
1 skill · 2 commands · 1 agent
Evidence-based C4 architecture in Structurizr: source discovery, scoped context/container/component views, saved routing, rendered geometry checks and reproducible local exports. Use when a system needs architecture diagrams grounded in its code and documents, or existing Structurizr views need clearer lines and labels.
1 skill · 2 commands · 1 agent
Agentic RAG methodology for Claude Code skills — how to structure large knowledge bases with SKILL.md as a thin router + sections/_index.md + 30-50 line content files. Use when building a skill with >300 lines or >5 topics. Includes 5+ anti-patterns, copy-pasteable starter-kit, and distribution recipes. Triggers on: agentic RAG, SKILL.md structure, sections pattern, skill methodology, knowledge base design, how to write a skill.
1 skill
Claude Code ecosystem reference — an opinionated guide to CLAUDE.md, plugins, agents, hooks, MCP and the anti-patterns, synthesised from audit findings across this marketplace. Use when authoring or debugging Claude Code configuration itself and you want what was actually measured here rather than what the surface suggests. Full history in CHANGELOG.md.
1 skill
Practical cookbook of forgeplan CLI recipes — task-oriented guides covering onboarding, PRD authoring, evidence patterns, workflow cycles, multi-plugin discipline, AI-pair dispatch, troubleshooting and a CLI/MCP quick reference, each shaped as goal -> command -> example -> common errors. Use when you know what you want from forgeplan and need the exact invocation, not the methodology behind it. Full history in CHANGELOG.md.
1 skill