@softspark/ai-toolkit 1.9.0 → 2.0.0

package/CHANGELOG.md

@@ -7,10 +7,30 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 
 ---
 
+## v2.0.0 — SoftSpark Namespace Migration (2026-04-12)
+
+### BREAKING CHANGES
+- **Home directory moved** — `~/.ai-toolkit/` → `~/.softspark/ai-toolkit/`. Prepares the namespace for sibling tools (`jira-mcp`, etc.) under `~/.softspark/`
+- **Per-project config renamed** — `.ai-toolkit.json` → `.softspark-toolkit.json`
+- **Per-project lock file renamed** — `.ai-toolkit.lock.json` → `.softspark-toolkit.lock.json`
+
+### Added
+- **Auto-migration** — on first `install`/`update` after upgrade, data is automatically migrated from legacy path. A `.migrated` marker is left in `~/.ai-toolkit/` pointing to the new location
+- **`scripts/paths.py`** — centralized path constants module; all scripts import from here instead of hardcoding paths
+- **`scripts/migrate.py`** — standalone migration script (`python3 scripts/migrate.py [--dry-run]`)
+- **Legacy fallback** — `config_resolver` and `config_lock` transparently read old filenames (`.ai-toolkit.json`, `.ai-toolkit.lock.json`) if new ones don't exist
+- **JS CLI fallback** — `ai-toolkit update` checks legacy `state.json` location for seamless first upgrade
+
+### Changed
+- All Python scripts, Bash hooks, JS CLI, hooks.json, manifest.json, tests, and documentation updated to use `~/.softspark/ai-toolkit/` paths
+- `AI_TOOLKIT_HOME` env var still supported as override
+
+---
+
 ## v1.9.0 — Project Registry & Doc Sync (2026-04-12)
 
 ### Added
-- **Project registry** — `install --local` automatically registers project path in `~/.ai-toolkit/projects.json`. `ai-toolkit update` propagates updates to all registered projects in parallel via `ThreadPoolExecutor`
+- **Project registry** — `install --local` automatically registers project path in `~/.softspark/ai-toolkit/projects.json`. `ai-toolkit update` propagates updates to all registered projects in parallel via `ThreadPoolExecutor`
 - **`ai-toolkit projects`** — list registered projects, `--prune` to remove stale (deleted directories), `remove <path>` to unregister specific project
 - **Parallel update propagation** — `ai-toolkit update` (global) now auto-updates all registered local projects concurrently (max 8 workers)
 
@@ -25,21 +45,21 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 ## v1.8.0 — Enterprise Config Inheritance (2026-04-12)
 
 ### Added
-- **Configuration inheritance system** — `extends` pattern (like ESLint/TypeScript) for multi-repo AI governance. Organizations define a shared base config published as npm package, git URL, or local path; projects inherit via `.ai-toolkit.json`
+- **Configuration inheritance system** — `extends` pattern (like ESLint/TypeScript) for multi-repo AI governance. Organizations define a shared base config published as npm package, git URL, or local path; projects inherit via `.softspark-toolkit.json`
 - **`ai-toolkit config validate`** — schema validation + extends resolution + enforcement check
 - **`ai-toolkit config diff`** — visual diff of project vs base config (profile, agents, rules, constitution, overrides)
-- **`ai-toolkit config init`** — interactive or flag-driven `.ai-toolkit.json` creation with extends validation
+- **`ai-toolkit config init`** — interactive or flag-driven `.softspark-toolkit.json` creation with extends validation
 - **`ai-toolkit config create-base`** — scaffolds ready-to-publish npm base config package (package.json, ai-toolkit.config.json, rules/, agents/, README)
 - **`ai-toolkit config check`** — CI enforcement gate with JSON output and exit codes (0=pass, 1=fail, 2=no config)
 - **Merge engine** — layered deep merge (base → project) with special handling for agents (requiredAgents enforcement), rules (union), constitution (immutability), enforce blocks (cannot weaken)
 - **Constitution immutability guard** — Articles I-V absolutely immutable; base config articles immutable; projects can only ADD new articles (6+)
 - **Override validation** — `override: true` + justification (min 20 chars) required; `forbidOverride` enforcement
 - **Enforce constraints** — 4 types: `minHookProfile`, `requiredPlugins`, `forbidOverride`, `requiredAgents`
-- **Lock file** (`.ai-toolkit.lock.json`) — pins resolved base config versions for reproducible installs across team; generated on `install --local`, updated on `update --local`
-- **Audit trail** — extends metadata recorded in `state.json` and `.ai-toolkit-extends.json`
-- **Offline fallback** — uses cached configs from `~/.ai-toolkit/config-cache/` when registry unavailable
+- **Lock file** (`.softspark-toolkit.lock.json`) — pins resolved base config versions for reproducible installs across team; generated on `install --local`, updated on `update --local`
+- **Audit trail** — extends metadata recorded in `state.json` and `.softspark-toolkit-extends.json`
+- **Offline fallback** — uses cached configs from `~/.softspark/ai-toolkit/config-cache/` when registry unavailable
 - **Cycle detection** — max 5-level extends chain with circular reference detection
-- **Install integration** — `install --local` and `update --local` auto-detect `.ai-toolkit.json`, resolve extends, merge, validate, inject rules + constitution amendments into generated files
+- **Install integration** — `install --local` and `update --local` auto-detect `.softspark-toolkit.json`, resolve extends, merge, validate, inject rules + constitution amendments into generated files
 - **New CLI flags** — `--config <path>` (explicit config file), `--refresh-base` (force re-fetch)
 - **JSON Schema** — `scripts/schemas/ai-toolkit-config.schema.json` for editor autocompletion
 - **Enterprise config guide** — `kb/reference/enterprise-config-guide.md` comprehensive documentation
@@ -82,7 +102,6 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 
 ### Added
 - **Language rules propagation to all IDE editors** — shared `dir_rules_shared.py` module now injects language-specific and registered rules into Cursor, Windsurf, Cline, Roo Code, Augment, Antigravity, and Copilot generators. All platforms receive identical rule content from a single source of truth.
-- **Local Dashboard Plan** — planning doc (`kb/planning/local-dashboard-plan.md`) for ai-toolkit UI with visual skill/agent management features
 - **Enterprise Config Inheritance Plan** — planning doc (`kb/planning/enterprise-config-inheritance-plan.md`) for hierarchical config system
 - **Offline SLM Profile Plan** — planning doc (`kb/planning/offline-slm-profile-plan.md`) for offline small language model profiles
 - **Cloud Security Pack Plan** — planning doc (`kb/planning/cloud-security-pack-plan.md`) for multi-cloud audit (GCP/AWS/Azure)
@@ -215,7 +234,7 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 ### Fixed
 - **Version check**: `ai-toolkit status` and session-start hook now read installed version from `state.json` instead of `package.json`, fixing false "up to date" when npm package was upgraded but `ai-toolkit update` not yet run.
 - **Version check**: `status` forces a fresh npm check (no 24h cache) so user always sees real state.
-- **Session-start hook**: `TOOLKIT_DIR` resolved via `npm root -g` instead of broken `../../` relative path from `~/.ai-toolkit/hooks/`.
+- **Session-start hook**: `TOOLKIT_DIR` resolved via `npm root -g` instead of broken `../../` relative path from `~/.softspark/ai-toolkit/hooks/`.
 
 ### Changed
 - **Notification hook**: replaced inline macOS-only `osascript` with cross-platform `notify-waiting.sh` script (macOS/Linux/Windows WSL).
@@ -241,7 +260,7 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 ## v1.3.10 — Patch (2026-04-07)
 
 ### Fixed
-- **Version cache**: `install` and `update` now clear `~/.ai-toolkit/version-check.json` so `status` shows correct "Latest" immediately after upgrade.
+- **Version cache**: `install` and `update` now clear `~/.softspark/ai-toolkit/version-check.json` so `status` shows correct "Latest" immediately after upgrade.
 
 ---
 
@@ -285,7 +304,7 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 ## v1.3.5 — Patch (2026-04-07)
 
 ### Fixed
-- **Stats not counting**: `track-usage.sh` and `user-prompt-submit.sh` now read prompt from stdin JSON (`.prompt` field) instead of non-existent `CLAUDE_USER_PROMPT` env var. Skill invocations are now properly tracked in `~/.ai-toolkit/stats.json`.
+- **Stats not counting**: `track-usage.sh` and `user-prompt-submit.sh` now read prompt from stdin JSON (`.prompt` field) instead of non-existent `CLAUDE_USER_PROMPT` env var. Skill invocations are now properly tracked in `~/.softspark/ai-toolkit/stats.json`.
 
 ---
 
@@ -320,7 +339,7 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 - **Language Rules System**: 70 language-specific coding rules across 13 languages (TypeScript, Python, Go, Rust, Java, Kotlin, Swift, Dart, C#, PHP, C++, Ruby) + 5 common rules. 5 categories per language: coding-style, testing, patterns, frameworks, security.
 - **MCP Templates**: 25 ready-to-use MCP server configuration templates (GitHub, PostgreSQL, Slack, Sentry, Context7, etc.) with CLI management (`ai-toolkit mcp add/list/show/remove`).
 - **Extension API**: `inject-hook` / `remove-hook` commands for external tools to inject hooks into settings.json with unique `_source` tags. Parallels existing `inject-rule` / `remove-rule`.
-- **Manifest-Driven Install**: Module-level install granularity (`--modules`), language auto-detection (`--auto-detect`), install state tracking (`~/.ai-toolkit/state.json`), `status` and `update` commands.
+- **Manifest-Driven Install**: Module-level install granularity (`--modules`), language auto-detection (`--auto-detect`), install state tracking (`~/.softspark/ai-toolkit/state.json`), `status` and `update` commands.
 - **6 new hooks**: `guard-config.sh` (config file protection), `mcp-health.sh` (MCP server health check), `governance-capture.sh` (security audit logging), `commit-quality.sh` (conventional commits advisory), `session-context.sh` (environment snapshot), `pre-compact-save.sh` (pre-compaction backup).
 - **`/council` skill**: 4-perspective decision evaluation (Advocate, Critic, Pragmatist, User-Proxy) for architectural decisions.
 - **`/introspect` skill**: Agent self-debugging with 7 failure pattern classification and recovery actions.
@@ -420,7 +439,7 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 - **`npx @softspark/ai-toolkit install`** — zero-friction trial without global install
 - `--dry-run` flag as alias for `--list` in install/update
 - MIT license — full open source, use/modify/distribute freely
-- Global install into `~/.claude/` with merge-friendly propagation; hooks merged into `settings.json`, scripts copied into `~/.ai-toolkit/hooks/`
+- Global install into `~/.claude/` with merge-friendly propagation; hooks merged into `settings.json`, scripts copied into `~/.softspark/ai-toolkit/hooks/`
 - Idempotent generators with `<!-- TOOLKIT:ai-toolkit START/END -->` markers
 - CI: auto-regenerate `AGENTS.md` and `llms.txt` on push to main; publish on tags
 - **DRY refactoring**: `scripts/_common.py` shared library for all generators and CLI scripts; `app/hooks/_profile-check.sh` for 9 hooks; CLI uses data-driven `GENERATORS` map
@@ -433,7 +452,7 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 - **Visual companion** for `/write-a-prd` and `/design-an-interface` — ephemeral local HTTP server renders mockups, diagrams, and comparisons in browser during brainstorming
 - **Memory plugin pack** (`app/plugins/memory-pack/`) — SQLite-based persistent memory across sessions with FTS5 full-text search, PostToolUse observation capture, Stop session summary, `<private>` tag privacy controls, and progressive disclosure (summary → details → full)
 - **`validate.py --strict`** — CI-grade validation treating warnings as errors, plus content quality checks (name=directory, non-empty body)
-- **`doctor.py` stale rules detection** (Check 8) — detects rules in CLAUDE.md whose source files no longer exist in `~/.ai-toolkit/rules/`
+- **`doctor.py` stale rules detection** (Check 8) — detects rules in CLAUDE.md whose source files no longer exist in `~/.softspark/ai-toolkit/rules/`
 - **Reasoning engine template** (`app/skills/skill-creator/templates/reasoning-engine/`) — generic Python stdlib search for domain skills with >50 categorized items, anti-pattern filtering, JSON stdout
 - **Dashboard template** (`app/skills/skill-creator/templates/dashboard/index.html`) — single-file HTML dashboard parsing `stats.json` with skill usage charts
 - **Anti-pattern registry format** documented at `kb/reference/anti-pattern-registry-format.md` — structured JSON schema with severity, auto-fixability, and conflict rules

package/README.md

@@ -178,7 +178,7 @@ ai-toolkit/
 │   │   ├── clean-code/  # knowledge skill (auto-loaded)
 │   │   └── ... (87 more)
 │   ├── rules/           # Auto-injected into your CLAUDE.md
-│   ├── hooks/           # Hook scripts (copied to ~/.ai-toolkit/hooks/)
+│   ├── hooks/           # Hook scripts (copied to ~/.softspark/ai-toolkit/hooks/)
 │   │   ├── session-start.sh      # MANDATORY reminder + session context
 │   │   ├── guard-destructive.sh  # Block rm -rf, DROP TABLE, etc.
 │   │   ├── guard-path.sh         # Block wrong-user path hallucination
@@ -210,7 +210,7 @@ ai-toolkit/
 └── CHANGELOG.md
 ```
 
-**Distribution model:** Symlink-based for agents/skills, copy-based for hooks. `~/.claude/agents/` and `~/.claude/skills/` contain per-file symlinks into the npm package. Hook scripts are copied to `~/.ai-toolkit/hooks/` and referenced from `~/.claude/settings.json`. Run `ai-toolkit update` after `npm install` — all projects pick up changes instantly. (See [Distribution Model](kb/reference/distribution-model.md))
+**Distribution model:** Symlink-based for agents/skills, copy-based for hooks. `~/.claude/agents/` and `~/.claude/skills/` contain per-file symlinks into the npm package. Hook scripts are copied to `~/.softspark/ai-toolkit/hooks/` and referenced from `~/.claude/settings.json`. Run `ai-toolkit update` after `npm install` — all projects pick up changes instantly. (See [Distribution Model](kb/reference/distribution-model.md))
 
 ---
 
@@ -309,7 +309,7 @@ Unlike other toolkits that put safety rules in documentation only, ai-toolkit en
 
 ### 2. Hooks as Executable Scripts
 
-Hook logic lives in `app/hooks/*.sh` — not inline JSON one-liners. Scripts are copied to `~/.ai-toolkit/hooks/` on install and referenced from `~/.claude/settings.json`. Easy to read, debug, and extend.
+Hook logic lives in `app/hooks/*.sh` — not inline JSON one-liners. Scripts are copied to `~/.softspark/ai-toolkit/hooks/` on install and referenced from `~/.claude/settings.json`. Easy to read, debug, and extend.
 
 **12 lifecycle events / 21 global hook entries:**
 
@@ -317,7 +317,7 @@ Hook logic lives in `app/hooks/*.sh` — not inline JSON one-liners. Scripts are
 |-------|--------|--------|
 | SessionStart | `session-start.sh` | MANDATORY rules reminder + session context + instincts |
 | SessionStart | `mcp-health.sh` | Check MCP server command availability (non-blocking warning) |
-| SessionStart | `session-context.sh` | Capture environment snapshot (pwd, git branch, versions) to `~/.ai-toolkit/sessions/current-context.json` |
+| SessionStart | `session-context.sh` | Capture environment snapshot (pwd, git branch, versions) to `~/.softspark/ai-toolkit/sessions/current-context.json` |
 | Notification | `notify-waiting.sh` | Cross-platform desktop notification |
 | PreToolUse | `guard-destructive.sh` | Block `rm -rf`, `DROP TABLE`, etc. |
 | PreToolUse | `guard-path.sh` | Block wrong-user path hallucination |
@@ -326,14 +326,14 @@ Hook logic lives in `app/hooks/*.sh` — not inline JSON one-liners. Scripts are
 | UserPromptSubmit | `user-prompt-submit.sh` | Prompt governance reminder for planning, research, and safe execution |
 | UserPromptSubmit | `track-usage.sh` | Record skill invocations to local stats |
 | PostToolUse | `post-tool-use.sh` | Lightweight validation reminders after edits |
-| PostToolUse | `governance-capture.sh` | Log security-sensitive operations to `~/.ai-toolkit/governance.log` (JSONL) |
+| PostToolUse | `governance-capture.sh` | Log security-sensitive operations to `~/.softspark/ai-toolkit/governance.log` (JSONL) |
 | Stop | `quality-check.sh` | Multi-language lint (ruff/tsc/phpstan/dart/go) |
 | Stop | `save-session.sh` | Persist session context for cross-session continuity |
 | TaskCompleted | `quality-gate.sh` | Block task completion on lint/type errors |
 | SubagentStart | `subagent-start.sh` | Narrow-scope reminder for spawned subagents |
 | SubagentStop | `subagent-stop.sh` | Completion checklist for subagent handoff |
 | PreCompact | `pre-compact.sh` | Smart compaction: prioritized context (instincts > tasks > git state > decisions) |
-| PreCompact | `pre-compact-save.sh` | Save timestamped context backup before compaction to `~/.ai-toolkit/compactions/` |
+| PreCompact | `pre-compact-save.sh` | Save timestamped context backup before compaction to `~/.softspark/ai-toolkit/compactions/` |
 | SessionEnd | `session-end.sh` | Persist a session-end handoff note |
 | TeammateIdle | *(inline)* | Completeness reminder |
 
@@ -586,7 +586,7 @@ ai-toolkit status                         # show installed modules and versions
 ai-toolkit update                         # incremental re-install (only changed modules)
 ```
 
-Install state is tracked in `~/.ai-toolkit/state.json`. See [`kb/reference/manifest-install.md`](kb/reference/manifest-install.md).
+Install state is tracked in `~/.softspark/ai-toolkit/state.json`. See [`kb/reference/manifest-install.md`](kb/reference/manifest-install.md).
 
 ---
 
@@ -614,7 +614,7 @@ All packs have `status: experimental`. Each has a `plugin.json` manifest and `RE
 
 ## Config Inheritance (`extends`)
 
-Enterprise-grade configuration inheritance for multi-repo AI governance. Organizations define a shared base config published as an npm package, Git URL, or local path. Projects inherit via `.ai-toolkit.json`:
+Enterprise-grade configuration inheritance for multi-repo AI governance. Organizations define a shared base config published as an npm package, Git URL, or local path. Projects inherit via `.softspark-toolkit.json`:
 
 ```json
 {
@@ -628,8 +628,8 @@ Enterprise-grade configuration inheritance for multi-repo AI governance. Organiz
 - **Constitution immutability** — Articles I-V and base articles cannot be modified; projects can only ADD new articles (6+)
 - **Enforce constraints** — `requiredAgents`, `forbidOverride`, `minHookProfile`, `requiredPlugins`
 - **Override validation** — requires explicit `override: true` + justification (min 20 chars)
-- **Lock file** — `.ai-toolkit.lock.json` pins resolved versions for reproducible installs
-- **Offline fallback** — uses cached configs from `~/.ai-toolkit/config-cache/` when registry unavailable
+- **Lock file** — `.softspark-toolkit.lock.json` pins resolved versions for reproducible installs
+- **Offline fallback** — uses cached configs from `~/.softspark/ai-toolkit/config-cache/` when registry unavailable
 
 ```bash
 ai-toolkit config create-base @mycompany/ai-toolkit-config  # scaffold base package
@@ -645,7 +645,7 @@ See [Enterprise Config Guide](kb/reference/enterprise-config-guide.md) for full
 
 ## Project Registry
 
-All projects installed with `--local` are automatically registered in `~/.ai-toolkit/projects.json`. Running `ai-toolkit update` propagates updates to all registered projects in parallel.
+All projects installed with `--local` are automatically registered in `~/.softspark/ai-toolkit/projects.json`. Running `ai-toolkit update` propagates updates to all registered projects in parallel.
 
 ```bash
 ai-toolkit projects              # list registered projects
@@ -802,17 +802,17 @@ Usage: ai-toolkit <command> [options]
 | `update` | Re-apply toolkit after `npm install -g @softspark/ai-toolkit@latest` |
 | `update --local` | Re-apply + auto-detect editors from existing project files |
 | `reset --local` | Wipe all project-local configs and recreate from scratch (clean slate) |
-| `add-rule <rule.md> [name]` | Register rule in `~/.ai-toolkit/rules/` — auto-applied on every `update` |
-| `remove-rule <name> [dir]` | Unregister rule from `~/.ai-toolkit/rules/` and remove its block from `CLAUDE.md` |
+| `add-rule <rule.md> [name]` | Register rule in `~/.softspark/ai-toolkit/rules/` — auto-applied on every `update` |
+| `remove-rule <name> [dir]` | Unregister rule from `~/.softspark/ai-toolkit/rules/` and remove its block from `CLAUDE.md` |
 | `inject-hook <file.json>` | Inject external hooks into settings.json (idempotent, `_source` tagged) |
 | `remove-hook <name>` | Remove injected hooks by source name |
 | `mcp list` | List available MCP server templates (25 templates) |
 | `mcp add <name> [names...]` | Add MCP server template(s) to `.mcp.json` |
 | `mcp show <name>` | Show MCP template config details |
 | `mcp remove <name>` | Remove MCP server from `.mcp.json` |
-| `config validate [path]` | Validate `.ai-toolkit.json` schema + extends + enforcement |
+| `config validate [path]` | Validate `.softspark-toolkit.json` schema + extends + enforcement |
 | `config diff [path]` | Show project vs base config differences |
-| `config init [flags]` | Create `.ai-toolkit.json` (`--extends`, `--profile`, `--no-extends`) |
+| `config init [flags]` | Create `.softspark-toolkit.json` (`--extends`, `--profile`, `--no-extends`) |
 | `config create-base <name>` | Scaffold base config npm package |
 | `config check [path]` | CI enforcement gate (exit 0=pass, 1=fail, 2=no config; `--json`) |
 | `projects` | List registered projects (`--prune` to clean stale, `remove <path>`) |
@@ -882,19 +882,19 @@ Any repo can register its rules so they are automatically injected into all AI t
 ```bash
 cd /path/to/your-repo
 ai-toolkit add-rule ./jira-rules.md
-# Registered: 'jira-rules' → ~/.ai-toolkit/rules/jira-rules.md
+# Registered: 'jira-rules' → ~/.softspark/ai-toolkit/rules/jira-rules.md
 
 ai-toolkit update
 # → injects jira-rules into ~/.claude/CLAUDE.md, ~/.cursor/rules, Windsurf, Gemini
 ```
 
-Rules are stored in `~/.ai-toolkit/rules/` and re-applied on every `update`. Injection is **idempotent** — re-running updates only the marked block, never touching content outside it.
+Rules are stored in `~/.softspark/ai-toolkit/rules/` and re-applied on every `update`. Injection is **idempotent** — re-running updates only the marked block, never touching content outside it.
 
 To unregister:
 
 ```bash
 ai-toolkit remove-rule jira-rules
-# Removes from ~/.ai-toolkit/rules/ and strips the block from ~/.claude/CLAUDE.md
+# Removes from ~/.softspark/ai-toolkit/rules/ and strips the block from ~/.claude/CLAUDE.md
 ```
 
 See [`kb/reference/integrations.md`](kb/reference/integrations.md) for known integrations.

package/app/ARCHITECTURE.md

@@ -307,7 +307,7 @@ Lead Session (You)
 ### Language Rules (70 files, 13 languages)
 `app/rules/` contains per-language coding rules. Supported languages: TypeScript, Python, Go, Rust, Java, Kotlin, Swift, Dart, C#, PHP, C++, Ruby, and common (shared). Auto-detected from project files via `--auto-detect` or selected with `--modules rules-<lang>`.
 
-Language rules are propagated to **all configured editors** — not just Claude. `dir_rules_shared.build_language_rules()` reads `app/rules/<lang>/*.md`, strips frontmatter, and returns combined content per language. Each directory-based generator (Cursor, Windsurf, Cline, Roo, Augment, Antigravity) emits `ai-toolkit-lang-<lang>` files in its native format. Registered custom rules (`~/.ai-toolkit/rules/`) are similarly propagated as `ai-toolkit-custom-<name>` files via `build_registered_rules()`.
+Language rules are propagated to **all configured editors** — not just Claude. `dir_rules_shared.build_language_rules()` reads `app/rules/<lang>/*.md`, strips frontmatter, and returns combined content per language. Each directory-based generator (Cursor, Windsurf, Cline, Roo, Augment, Antigravity) emits `ai-toolkit-lang-<lang>` files in its native format. Registered custom rules (`~/.softspark/ai-toolkit/rules/`) are similarly propagated as `ai-toolkit-custom-<name>` files via `build_registered_rules()`.
 
 ### Extension API (`inject-hook`)
 The `inject_section_cli.py` script provides a stable marker-based injection API. Any tool can add sections to `CLAUDE.md`, `constitution.md`, or `ARCHITECTURE.md` without overwriting user content, using `<!-- TOOLKIT:START:<id> -->` / `<!-- TOOLKIT:END:<id> -->` markers.
@@ -316,10 +316,10 @@ The `inject_section_cli.py` script provides a stable marker-based injection API.
 `scripts/compile_slm.py` compiles the full toolkit (20K+ tokens) into a minimal system prompt for Small Language Models (2K-16K tokens). Pipeline: Parse → Score → Compress → Pack → Emit. Supports 4 compression levels (ultra-light, light, standard, extended), 4 output formats (raw, ollama, json-string, aider), persona-aware scoring, and language-aware rule filtering. Profile `offline-slm` in `manifest.json`. Constitution is always included (non-negotiable).
 
 ### Config Inheritance (`extends`)
-`scripts/config_resolver.py`, `config_merger.py`, `config_validator.py`, `config_cli.py`, `config_scaffold.py`, `config_lock.py`. Enterprise configuration inheritance via `.ai-toolkit.json` `extends` field. Resolves base configs from npm packages, Git URLs, or local paths. Layered deep merge with constitution immutability (Articles I-V absolute), enforce constraints (`requiredAgents`, `forbidOverride`, `minHookProfile`), override validation (`override: true` + justification), and lock file (`.ai-toolkit.lock.json`). CLI: `config validate`, `config diff`, `config init`, `config create-base`, `config check`. Integrated into `install --local` and `update --local` flows.
+`scripts/config_resolver.py`, `config_merger.py`, `config_validator.py`, `config_cli.py`, `config_scaffold.py`, `config_lock.py`. Enterprise configuration inheritance via `.softspark-toolkit.json` `extends` field. Resolves base configs from npm packages, Git URLs, or local paths. Layered deep merge with constitution immutability (Articles I-V absolute), enforce constraints (`requiredAgents`, `forbidOverride`, `minHookProfile`), override validation (`override: true` + justification), and lock file (`.softspark-toolkit.lock.json`). CLI: `config validate`, `config diff`, `config init`, `config create-base`, `config check`. Integrated into `install --local` and `update --local` flows.
 
 ### Project Registry
-`scripts/install_steps/project_registry.py`, `scripts/update_projects.py`, `scripts/projects_cli.py`. Tracks all `--local` installed projects in `~/.ai-toolkit/projects.json`. `ai-toolkit update` propagates to all registered projects in parallel via `ThreadPoolExecutor`. CLI: `ai-toolkit projects`, `--prune`, `remove <path>`.
+`scripts/install_steps/project_registry.py`, `scripts/update_projects.py`, `scripts/projects_cli.py`. Tracks all `--local` installed projects in `~/.softspark/ai-toolkit/projects.json`. `ai-toolkit update` propagates to all registered projects in parallel via `ThreadPoolExecutor`. CLI: `ai-toolkit projects`, `--prune`, `remove <path>`.
 
 ### Manifest Install (`--modules`, `--auto-detect`)
 `manifest.json` defines all installable components as named modules. Install individual modules with `ai-toolkit install --modules <name>` or let the installer detect which language rules to add based on project files (e.g. `package.json` → `rules-typescript`, `go.mod` → `rules-golang`).

package/app/hooks/governance-capture.sh

@@ -8,7 +8,7 @@
 # shellcheck source=_profile-check.sh
 source "$(dirname "$0")/_profile-check.sh"
 
-LOG_DIR="$HOME/.ai-toolkit"
+LOG_DIR="$HOME/.softspark/ai-toolkit"
 LOG_FILE="$LOG_DIR/governance.log"
 TIMESTAMP=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
 SESSION="${CLAUDE_SESSION_ID:-unknown}"

package/app/hooks/pre-compact-save.sh

@@ -8,7 +8,7 @@
 # shellcheck source=_profile-check.sh
 source "$(dirname "$0")/_profile-check.sh"
 
-SAVE_DIR="$HOME/.ai-toolkit/compactions"
+SAVE_DIR="$HOME/.softspark/ai-toolkit/compactions"
 mkdir -p "$SAVE_DIR"
 
 # Read from stdin (Claude Code passes JSON with .session_id)

package/app/hooks/session-context.sh

@@ -12,7 +12,7 @@ source "$(dirname "$0")/_profile-check.sh"
 INPUT=$(cat)
 SESSION=$(echo "$INPUT" | jq -r '.session_id // empty' 2>/dev/null)
 [ -z "$SESSION" ] && SESSION="$$"
-SESSIONS_DIR="$HOME/.ai-toolkit/sessions"
+SESSIONS_DIR="$HOME/.softspark/ai-toolkit/sessions"
 mkdir -p "$SESSIONS_DIR"
 
 CONTEXT_FILE="$SESSIONS_DIR/${SESSION}.json"

package/app/hooks/track-usage.sh

@@ -2,12 +2,12 @@
 # track-usage.sh — Track skill invocations for usage stats.
 #
 # Fires on: UserPromptSubmit
-# Writes to: ~/.ai-toolkit/stats.json
+# Writes to: ~/.softspark/ai-toolkit/stats.json
 #
 # Detects /skill-name pattern from user prompt and increments counter.
 # Uses atomic write via python3 os.replace() to prevent corruption.
 
-STATS_FILE="${HOME}/.ai-toolkit/stats.json"
+STATS_FILE="${HOME}/.softspark/ai-toolkit/stats.json"
 
 # Read prompt from stdin (Claude Code passes JSON with .prompt field)
 INPUT=$(cat)

package/app/hooks.json

@@ -7,7 +7,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/session-start.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/session-start.sh\""
                     }
                 ]
             },
@@ -17,7 +17,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/mcp-health.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/mcp-health.sh\""
                     }
                 ]
             },
@@ -27,7 +27,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/session-context.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/session-context.sh\""
                     }
                 ]
             }
@@ -39,7 +39,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "bash ~/.ai-toolkit/hooks/notify-waiting.sh"
+                        "command": "bash ~/.softspark/ai-toolkit/hooks/notify-waiting.sh"
                     }
                 ]
             }
@@ -51,7 +51,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/guard-destructive.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/guard-destructive.sh\""
                     }
                 ]
             },
@@ -61,7 +61,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/guard-path.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/guard-path.sh\""
                     }
                 ]
             },
@@ -71,7 +71,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/guard-config.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/guard-config.sh\""
                     }
                 ]
             },
@@ -81,7 +81,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/commit-quality.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/commit-quality.sh\""
                     }
                 ]
             }
@@ -93,7 +93,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/user-prompt-submit.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/user-prompt-submit.sh\""
                     }
                 ]
             },
@@ -103,7 +103,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/track-usage.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/track-usage.sh\""
                     }
                 ]
             }
@@ -115,7 +115,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/post-tool-use.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/post-tool-use.sh\""
                     }
                 ]
             },
@@ -125,7 +125,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/governance-capture.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/governance-capture.sh\""
                     }
                 ]
             }
@@ -137,7 +137,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/quality-check.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/quality-check.sh\""
                     }
                 ]
             },
@@ -147,7 +147,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/save-session.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/save-session.sh\""
                     }
                 ]
             }
@@ -159,7 +159,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/quality-gate.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/quality-gate.sh\""
                     }
                 ]
             }
@@ -183,7 +183,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/subagent-start.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/subagent-start.sh\""
                     }
                 ]
             }
@@ -195,7 +195,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/subagent-stop.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/subagent-stop.sh\""
                     }
                 ]
             }
@@ -207,7 +207,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/pre-compact.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/pre-compact.sh\""
                     }
                 ]
             },
@@ -217,7 +217,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/pre-compact-save.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/pre-compact-save.sh\""
                     }
                 ]
             }
@@ -229,7 +229,7 @@
                 "hooks": [
                     {
                         "type": "command",
-                        "command": "\"$HOME/.ai-toolkit/hooks/session-end.sh\""
+                        "command": "\"$HOME/.softspark/ai-toolkit/hooks/session-end.sh\""
                     }
                 ]
             }

package/app/plugins/memory-pack/README.md

@@ -8,7 +8,7 @@ Persistent session memory with SQLite storage and full-text search.
 - Scripts: `init_db.py` (database setup), `strip_private.py` (privacy filter)
 
 ## How It Works
-1. **Capture**: Every tool use is recorded to `~/.ai-toolkit/memory.db` (PostToolUse hook)
+1. **Capture**: Every tool use is recorded to `~/.softspark/ai-toolkit/memory.db` (PostToolUse hook)
 2. **Summarize**: Session summary generated on each Stop hook (tools used, observation count, time range)
 3. **Search**: `/mem-search <query>` runs FTS5 full-text search with progressive disclosure
 4. **Privacy**: Content between `<private>...</private>` tags is stripped before storage

package/app/plugins/memory-pack/hooks/observation-capture.sh

@@ -6,8 +6,8 @@
 # Strips private tags, truncates to 2000 chars, inserts into observations table.
 # Never blocks the user — always exits 0.
 
-DB_PATH="${HOME}/.ai-toolkit/memory.db"
-STRIP_PRIVATE="${HOME}/.ai-toolkit/plugin-scripts/memory-pack/strip_private.py"
+DB_PATH="${HOME}/.softspark/ai-toolkit/memory.db"
+STRIP_PRIVATE="${HOME}/.softspark/ai-toolkit/plugin-scripts/memory-pack/strip_private.py"
 MAX_CONTENT_LENGTH=2000
 
 # Bail silently if database does not exist

package/app/plugins/memory-pack/hooks/session-summary.sh

@@ -7,7 +7,7 @@
 # Auto-prunes observations older than RETENTION_DAYS (default 90).
 # Never blocks the user — always exits 0.
 
-DB_PATH="${HOME}/.ai-toolkit/memory.db"
+DB_PATH="${HOME}/.softspark/ai-toolkit/memory.db"
 RETENTION_DAYS="${MEMORY_RETENTION_DAYS:-90}"
 
 # Read JSON input from stdin (Claude Code hook protocol)

package/app/plugins/memory-pack/scripts/init_db.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 """Initialize SQLite memory database for ai-toolkit memory-pack.
 
-Creates ~/.ai-toolkit/memory.db with sessions, observations, and FTS5 tables.
+Creates ~/.softspark/ai-toolkit/memory.db with sessions, observations, and FTS5 tables.
 Safe to run multiple times (uses IF NOT EXISTS).
 
 Usage: python3 app/plugins/memory-pack/scripts/init_db.py
@@ -11,7 +11,7 @@ from __future__ import annotations
 import sqlite3
 from pathlib import Path
 
-DB_DIR = Path.home() / ".ai-toolkit"
+DB_DIR = Path.home() / ".softspark" / "ai-toolkit"
 DB_PATH = DB_DIR / "memory.db"
 
 SCHEMA = """

package/app/plugins/memory-pack/skills/mem-search/SKILL.md

@@ -15,7 +15,7 @@ $ARGUMENTS
 
 ## How It Works
 
-This skill queries the SQLite FTS5 full-text search index at `~/.ai-toolkit/memory.db` to find relevant observations from past sessions.
+This skill queries the SQLite FTS5 full-text search index at `~/.softspark/ai-toolkit/memory.db` to find relevant observations from past sessions.
 
 ## Instructions
 
@@ -23,12 +23,12 @@ This skill queries the SQLite FTS5 full-text search index at `~/.ai-toolkit/memo
 
 2. **Initialize the database** if it does not exist:
    ```bash
-   python3 "$HOME/.ai-toolkit/hooks/../plugins/memory-pack/scripts/init_db.py" 2>/dev/null || true
+   python3 "$HOME/.softspark/ai-toolkit/hooks/../plugins/memory-pack/scripts/init_db.py" 2>/dev/null || true
    ```
 
 3. **Run the FTS5 search** against the observations table:
    ```bash
-   sqlite3 ~/.ai-toolkit/memory.db "
+   sqlite3 ~/.softspark/ai-toolkit/memory.db "
      SELECT o.id, o.session_id, o.tool_name, o.content, o.created_at,
             s.project_dir, s.summary
      FROM observations_fts fts

package/app/skills/hook-creator/SKILL.md

@@ -57,7 +57,7 @@ Create a new Claude Code hook following ai-toolkit conventions.
     "hooks": [
         {
             "type": "command",
-            "command": "\"$HOME/.ai-toolkit/hooks/{script-name}.sh\""
+            "command": "\"$HOME/.softspark/ai-toolkit/hooks/{script-name}.sh\""
         }
     ]
 }
@@ -67,7 +67,7 @@ Required fields:
 - `_source`: always `"ai-toolkit"` (used by merge/strip logic)
 - `matcher`: tool name or regex for Pre/PostToolUse, empty string for global events
 - `hooks[].type`: always `"command"`
-- `hooks[].command`: path to script using `$HOME/.ai-toolkit/hooks/` prefix
+- `hooks[].command`: path to script using `$HOME/.softspark/ai-toolkit/hooks/` prefix
 
 ## Script Template
 

package/app/skills/mem-search/SKILL.md

@@ -15,7 +15,7 @@ $ARGUMENTS
 
 ## How It Works
 
-This skill queries the SQLite FTS5 full-text search index at `~/.ai-toolkit/memory.db` to find relevant observations from past sessions.
+This skill queries the SQLite FTS5 full-text search index at `~/.softspark/ai-toolkit/memory.db` to find relevant observations from past sessions.
 
 ## Instructions
 
@@ -23,12 +23,12 @@ This skill queries the SQLite FTS5 full-text search index at `~/.ai-toolkit/memo
 
 2. **Initialize the database** if it does not exist:
    ```bash
-   python3 "$HOME/.ai-toolkit/hooks/../plugins/memory-pack/scripts/init_db.py" 2>/dev/null || true
+   python3 "$HOME/.softspark/ai-toolkit/hooks/../plugins/memory-pack/scripts/init_db.py" 2>/dev/null || true
    ```
 
 3. **Run the FTS5 search** against the observations table:
    ```bash
-   sqlite3 ~/.ai-toolkit/memory.db "
+   sqlite3 ~/.softspark/ai-toolkit/memory.db "
      SELECT o.id, o.session_id, o.tool_name, o.content, o.created_at,
             s.project_dir, s.summary
      FROM observations_fts fts