ForgePlan-marketplace

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).

Flagship workflow plugin for the ForgePlan ecosystem. 40 engineering skills + dev-advisor agent + 5 hooks (+ smith greeting + insight watchdog). v1.49.0: NEW /forge-heal skill — PRD-074/RFC-020 brick 2 (Layer 4 heal-or-task): propose-not-silent 3-tier dispatch of findings onto PRD-032 AUTO/ADI/USER — AUTO auto-fixes ONLY 2 reversible kinds (phase_mismatch, complete stuck_draft) after a batch confirm + journal + one-call rollback (phase rollback via phase_advance --to prior, NOT undo_last); ADI reasons; USER writes a tracked NOTE-013 task + suggests the agent; never silent-mutates the tree. v1.48.0: NEW /forge-insight skill + insight-watchdog SessionStart hook — PRD-074/RFC-019 brick 1 self-aware integrity: filtered anomaly digest (silent when clean), accurate session counts from forgeplan truth (retires the stale-grep draft-count falsehood), NOTE-013 machine-findings ledger; plus a decay-reminder.sh stale --output/--kind flag fix (its ADR-trigger scan was silently no-opping). v1.46.0: NEW /conformance-vectors skill (SDD optional enrichment — ADR-008 / PRD-072 FR-006 / DEFER-012): the `## Conformance Vectors` convention (frozen language-neutral corpus = sole oracle) + a corpus-agnostic generic harness (freeze + conformance + cross-language equivalence gates, live negative-control-verified) + the proven 4-language semver reference promoted from sandbox (EVID-119) + a cross-language equivalence guardian-gate for multi-language SPECs. v1.45.0: /autorun RIPER methodology gate (DEFER-016 / RFC-018 FR-4) — a Row-4 (non-trivial production bug → RIPER, hook-gate=No) task makes the Plan→Execute transition human_required; autopilot HOLDS before the first Execute dispatch (unattended default = WAIT, not proceed) + checkpoint + CONCERNS EVIDENCE; closes the EVID-167 F1 / G8 autonomous-RIPER gap. v1.44.1: /riper FR-5 pin-hash basis clarified — hash the Research NOTE body content (sections, excluding mutable frontmatter), NOT the projection file (which false-stales on unrelated activation/link/score); + F2 note (the orchestrator records the Research NOTE; research-analyst is read-only Profile C) — DEFER-018 / EVID-172 F1+F2. v1.44.0: RIPER instance #4 (RFC-018 / ADR-010) — /riper formalized into the contract instance (C1-C6 + non-freezable Research C4+C6 + Plan-gate pin-freshness + per-mode hard constraints + hook-gate=No main-session orchestration), smith Row 4 reframe + disambiguator, /methodology-check Step 10 recognizes the Research ## Pinned revision C6; the ADR-012 internal codename is rendered hook-gate in all shipped artifacts. v1.43.0: smith routing-map Row 3 (new feature in existing service) reframed as the explicit SPARC instance — master-coordinated sparc-orchestrator dispatch + mandatory per-gate independent C4 + Pseudocode-absorption + Refinement→TDD delegation + SPARC/BMAD/TDD/Strangler disambiguator (RFC-016/ADR-010 instance #3). v1.42.0: smith routing-map Row 1 (greenfield) reframed as the explicit BMAD instance — master-coordinated agents-bmad dispatch + 3 mandatory C4 gates + BMAD/SPARC/TDD/Strangler disambiguator (RFC-013/ADR-010 instance #2). v1.41.1: smith routing-map adds a 'TDD-first feature' context row routing to the agents-tdd dispatch sequence (RFC-012/ADR-010). v1.41.0: /spec-author skill (ADR-008 light-path SDD; frozen #### Scenario = oracle) merged alongside the FR-3 ground-truth clause (PRs #130 + #131). v1.40.0: RFC-011 FR-3 ground-truth verification clause (generator≠verifier) — AGENT-AUTHORING-GUIDE adds canonical 'Profile B Step 4.5' section (variants A/A'/A'' + `## Ground-truth verification` EVID template + Profile B universal HARD RULE 8 making ML-13 enforceable: empty git diff on a claimed change = BLOCKER even when tests are green); smith routing-map adds 'Ground-truth verification (generator≠verifier)' methodology card applying to every Build/Audit row; corrected the worktree under-claim (isolation works for standalone subagents + Workflow + AgentTeams teammates, not coder-only — real risks are leak + assume-without-verify). Refs PROB-002/RFC-011/ADR-009; smoke `sandbox-verify/r3-reviewer-groundtruth-smoke.sh`. v1.38.1: cookbook §07 fix — final-e2e found CLI vs MCP agent-id validator asymmetry on forgeplan 0.32.1 (filed as forgeplan#353). Cookbook §07.1 example switched from 'adr-architect/1.11.1' (CLI rejects) to dash-form 'adr-architect-v1-11-1' (both accept). §14.4 added documenting the asymmetry + workaround. §14.5/14.6/14.7 renumbered. v1.38.0: NEW `/forgeplan-cookbook` skill — agentic-RAG router for 66 mcp__forgeplan__* MCP tools + 82 forgeplan CLI subcommands. 14 sections by use-case (lifecycle / discovery / quality / pipeline-health / session-phase / AI-driven / multi-agent / brownfield / activity / FPF / playbooks / plugins / release / MCP-safety) + flat alphabetical _index. Quick router maps intent → section. Section 14 documents 3 filed upstream bugs (#348 score-all hint, #350 CRITICAL @filepath data loss, #351 plugins doctor syntax) + canonical safe patterns. v1.37.1: CRITICAL safety convention — AGENT-AUTHORING-GUIDE now documents the MCP `body` parameter as literal-string-only (forgeplan#350 silent data-loss bug). Canonical safe pattern: Read file via host CLI, pass content as string. CLI vs MCP semantics table prevents agent confusion. Profile A/B/D agents are most exposed (canonical body writers). v1.37.0: --help-driven verification + Step 1b uses native `forgeplan migrate-secrets --apply` for LLM key import (PRD-077 FR-023 Part B). 4-row table covers: gemini (default template match), anthropic, openai, or no-key-found path. Removes 35-line manual config snippet — auto-import is the canonical forgeplan flow. v1.36.0: deep-e2e fix pack — (a) templates/smith-bootstrap.md acceptance probes use --type (4 places) — was --kind=, drifted from SKILL.md fix in v1.35.2; (b) new Step 1b in smith-bootstrap probes .forgeplan/config.yaml for an llm: block right after forgeplan init; if absent, prints informational guidance (3 providers — Anthropic / Gemini / OpenAI — with full config + secrets.env example) so the user can configure before the first /forge-cycle Step 4.5 ADI call; (c) Failure modes covers downstream LLM-not-configured halt. Closes deep-e2e findings 2 and 4. v1.35.2: e2e-test fix pack — smith-bootstrap Step 5/6 acceptance probes use correct CLI flag `--type` (not `--kind` — that name only exists in MCP forgeplan_new(kind=...) form), Step 6 documents the literal section names forgeplan validate MUST-requires (Problem statement, Target audience, Goals/Success Criteria, Functional Requirements with literal capitalisation, Out of scope, Related Artifacts) + cites the validator rule names that trigger on miss, and adds `forgeplan validate PRD-NNN → PASS` to acceptance criteria. v1.35.1: smoke-test fix — Step 0c 6th state `plugin-handles-it` (fpl-hsmem enabled + no project-local .mcp.json hindsight block = normal/healthy, not unclassified). Smoke against fresh tmp project surfaced that the previous 5-state matrix marked this normal case as 'UNCLASSIFIED'. Reference implementation now ships as bash if/elif ladder with explicit precedence order. v1.35.0: MCP-wiring drift closure trio — (1) /fpl-init Step 5 migrated from Python merge to native `forgeplan mcp install --client claude --scope project` (same primitive as smith-bootstrap Step 0b, eliminates skill-to-skill drift); (2) hooks bundle expanded from 1 to 3 files (safety-hook + pre-pr-evidence-check + forge-safety-hook) at templates/hooks/; (3) AGENTS.md MCP server registration section now leads with `forgeplan mcp install` as canonical wiring command across Claude Code / Cursor / Windsurf / Gemini / Codex. v1.34.0: smith-bootstrap Step 0 refactored from halt-and-instruct to active infrastructure runner. 5 sub-steps: 0a plugin enablement gate (halt-only on MUST miss), 0b forgeplan MCP auto-wire via native `forgeplan mcp install --client claude --scope project` (replaces halt + Python merge), 0c Hindsight detection with 5-state classification (fully wired / key missing / env-var naming mismatch / Docker quick-start / plugin not enabled) — informational guidance, never writes secrets, 0d minimal hooks bundle copy from templates/hooks/ (safety-hook.sh starter), 0e user-driven /reload-plugins + ToolSearch verify. Closes real-project gap observed 2026-05-20 where bootstrap landed CLAUDE.md+AGENTS.md but skipped MCP wiring → downstream agents shell-fallback → degraded artifacts. v1.33.0: smith-bootstrap pre-flight gates. v1.31.1: EPIC-002 niceties patch. v1.31.0: EPIC-002 — 4 smith skills + templates + session-start.sh.

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.

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.

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).

Structured engineering workflow for forgeplan users. Provides /forge-cycle (full SDLC cycle: Hindsight v2 memory bootstrap + parallel subagent dispatch via forgeplan_dispatch + Task tool + multi-reviewer audit with 4 parallel agents + mail-as-beads autonomous decisions logging + MCP-first per PRD-021/022 + claim/release per PRD-020 — implements RFC-003/PRD-025) and /forge-audit (multi-expert review), methodology knowledge base, quality gate hooks. Requires forgeplan CLI. v1.12.0: Sprint Z7 PRD-059 — /forge-cycle Step 4.5 FPF ADI mandatory for Standard+ (≥3 hypotheses required; guardian BLOCKER when no ADI EVID). v1.11.0: Sprint Z6 PRD-057 — /forge-cycle Step 6.5 BMAD adversarial review mandatory for Standard+ (guardian BLOCKER when zero Profile B EVID). v1.10: PRD-034 Sprint F — /forge-cycle template clarified (Anomaly #1 fix) + Phase 6.7/Step 7.7 live-smoke discipline check (Anomaly #11 wiring). v1.9.1: forge-advisor agent canonical-lint compliant.

[DEPRECATED — superseded by fpl-skills] Universal engineering toolkit: multi-expert audit, wave-based sprints, session context recall, card-based structured reports with auto-trigger hooks, and safety hooks. Works with any project and language. New users: install fpl-skills@ForgePlan-marketplace instead. v1.6.3: dev-advisor 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).

Brownfield extraction pack for forgeplan — turns legacy code + docs into a structured forgeplan graph. Ships 12 extraction skills (ubiquitous-language, use-case-miner, intent-inferrer, invariant-detector, causal-linker, hypothesis-triangulator, interview-packager, scenario-writer, kg-curator, canonical-reproducer, reproducibility-validator, rag-packager), 2 orchestration playbooks (extract-business-logic, phase-transitions), 3 integration recipes (autoresearch hooks, forgeplan MCP additions, RAG export), 5 mappings (c4-to-forge, ddd-to-forge, madr-to-forge, obsidian-to-forge, autoresearch-to-forge), templates, examples, and methodology docs. Implements two-tier extraction (Factum vs Intent) with confidence taxonomy and ADI cycle. v1.4.0: Sprint V (PRD-048) — discover agent migrated from standalone to plugin (canonical Profile A pattern, MCP-first 7-phase procedure, 9 brownfield MCP primitives wired).

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).

Domain-specific language and framework specialist agents. Provides expert-level guidance for TypeScript, Go, React, Next.js, Electron, embedded systems, fullstack, game dev, mobile, and WebSocket engineering. v1.1: 11 agents canonical-lint compliant (LR-1 model:sonnet, LR-2 hex colors, LR-3 bilingual descriptions with triggers).

Professional specialist agents: security experts, architecture reviewers, creative tools, research analysts, infrastructure engineers, plus pipeline-canonical roles. v1.12.0: RFC-011 FR-3 — ground-truth verification clause (Step 4.5 + HARD RULE + ## Ground-truth verification EVID section) added to 5 Profile B reviewers (security-expert, architect-reviewer, system-dev, evidence-recorder, artifact-reviewer) + guardian gate row; empty git diff on a claimed change is a BLOCKER even when tests are green (PROB-002 / ADR-009 / ML-13). v1.11.0: EPIC-003 / Sprint AA PRD-067/069 — guardian Step 5 verdict matrix +2 new rows: C4 CONCERNS (≥3-module ADR without docs/c4 file, Sprint Z9 PRD-060 implementation) + OpenSpec BLOCKER (supersede without ## Delta-spec, Sprint Z8 PRD-058 activation gate). Closes G2+G4 methodology auto-enforcement gaps. v1.10.1: EPIC-002 niceties patch. v1.10.0: EPIC-002 PRD-062 — new `smith` master-orchestrator agent (Profile B-orchestrator). v1.9.4: Sprint Z9 — adr-architect C4 dispatch. v1.9.3: Sprint Z7 — guardian ADI BLOCKER row.

GitHub operations agents: PR management, issue tracking, release automation, multi-repo coordination, project boards, workflow engineering, and repo architecture. v1.1: 7 agents canonical-lint compliant (LR-1..LR-3) — sonnet model, hex colors, bilingual EN/RU/Triggers descriptions.

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).

v0.2.1: tdd-orchestrator denylist adds forgeplan_validate - B-orchestrator parity (DEFER-015 / EVID-157 F1): a master coordinates, it does not validate; now matches smith/sparc + the AGENT-AUTHORING-GUIDE canon. Enforced-TDD methodology: tdd-orchestrator master + RED/GREEN phase agents + fail-closed PreToolUse gate (first instance of the AD/AID-PDLC sub-cycle contract). Implements RFC-012 / ADR-010: tdd-planner (scenarios→plan) + coder-tdd (plan→failing tests, RED) + tdd-test-validator (independent C4 verifier) + PreToolUse tdd-gate (permissionDecision:deny, exit2 fail-closed) + normalized full-file SPEC hash freeze (FR-6).

v0.1.2: ADR-012 internal codename rendered hook-gate in shipped artifacts — bmad-orchestrator + bmad-gate.sh comment; terminology only, no behavior change. v0.1.1: bmad-orchestrator denylist adds forgeplan_validate - B-orchestrator parity (DEFER-015 / EVID-157 F1); now matches smith/sparc + the AGENT-AUTHORING-GUIDE canon. BMAD greenfield methodology: bmad-orchestrator master walks the persona arc (Analyst → PM → Architect → Scrum-Master → Dev → QA) with a blocking quality-gate at every handoff and a fail-closed no-code-before-plan PreToolUse gate (second instance of the AD/AID-PDLC sub-cycle contract). Implements RFC-013 / ADR-010: reuses existing forgeplan-aware personas (brief-intake/specification/adr-architect/architecture/goal-planner/coder/tester/code-reviewer/guardian/evidence-recorder) + a new bmad-orchestrator + /bmad + /bmad-init + bmad-gate (permissionDecision:deny, exit2 fail-closed) reading a per-branch phase state file.

Claude Code ecosystem reference — opinionated agentic-RAG guide for CLAUDE.md, plugins, agents, hooks, MCP, and anti-patterns. Synthesises 47+ audit findings from ForgePlan marketplace work. v1.1.0: all 6 sections authored — claude-md + plugins + agents + hooks + mcp + anti-patterns (RFC-005..009 closed / DEFER-005..009).