@softspark/ai-toolkit 4.19.0 → 4.20.0

package/llms.txt

@@ -14,19 +14,22 @@
 - [Best Practices](kb/best-practices/README.md)
 - [No Hardcoded Counts in Secondary Docs](kb/best-practices/no-hardcoded-counts.md)
 - [Plan: Deep Coverage v3.0 — 100% Native Surface Utilization](kb/history/completed/deep-coverage-v3-20260423.md)
+- [Plan: Drop Cascade hooks after 2026-07-01 sunset](kb/history/completed/drop-cascade-hooks-after-sunset-20260710.md)
 - [Plan: Ecosystem Deep Sweep — All 12 Supported Tools](kb/history/completed/ecosystem-deep-sweep-20260423.md)
 - [Plan: Enterprise Config Inheritance — Multi-Repo Governance with `extends`](kb/history/completed/enterprise-config-inheritance-plan-20260412.md)
 - [Spike: F2 MCP Context Trim — Hook Feasibility & Path Decision](kb/history/completed/f2-mcp-trim-spike-20260504.md)
+- [Language Plugin Packs — REMOVED](kb/history/completed/language-packs-removed-20260727.md)
+- [PRD: MCP Context Trim v4.0 — ABANDONED](kb/history/completed/mcp-context-trim-v4-prd-obsoleted-20260727.md)
 - [Implementation Plan: Native Tool Output Filter](kb/history/completed/native-tool-output-filter-plan.md)
+- [Removed: Nine Plugin Packs That Installed Nothing](kb/history/completed/no-op-plugin-packs-removed-20260727.md)
 - [Plan: Offline-First SLM Profile — Lightweight Mode for Local Models](kb/history/completed/offline-slm-profile-plan-20260411.md)
 - [Retirement: Native Tool-Output Filter](kb/history/completed/output-filter-retirement-20260726.md)
 - [Plan: Output & Token Discipline](kb/history/completed/output-token-discipline-plan-20260504.md)
 - [rtk Pack Integration](kb/history/completed/rtk-pack-integration-20260726.md)
 - [Retirement: rtk-pack](kb/history/completed/rtk-pack-retirement-20260727.md)
+- [Closed: Tool-Output Token Reduction](kb/history/completed/tool-output-token-reduction-closed-20260727.md)
 - [How-To Guides](kb/howto/README.md)
 - [Plan: Cloud Security Pack — Multi-Cloud Audit](kb/planning/cloud-security-pack-plan.md)
-- [Plan: Drop Cascade hooks after 2026-07-01 sunset](kb/planning/drop-cascade-hooks-after-sunset.md)
-- [PRD: MCP Context Trim v4.0](kb/planning/mcp-context-trim-v4-prd.md)
 - [SOP: Ecosystem Sync](kb/procedures/ecosystem-sync-sop.md)
 - [SOP: AI Toolkit Maintenance](kb/procedures/maintenance-sop.md)
 - [SOP: Post-Release Testing](kb/procedures/post-release-testing-sop.md)
@@ -51,8 +54,8 @@
 - [Hierarchical Override Pattern](kb/reference/hierarchical-override-pattern.md)
 - [Hooks Catalog](kb/reference/hooks-catalog.md)
 - [External Integrations](kb/reference/integrations.md)
-- [Language Plugin Packs](kb/reference/language-packs.md)
 - [Language Rules System](kb/reference/language-rules.md)
+- [Licensing](kb/reference/licensing.md)
 - [Manifest-Driven Install System](kb/reference/manifest-install.md)
 - [MCP Editor Compatibility](kb/reference/mcp-editor-compatibility.md)
 - [MCP Server Templates](kb/reference/mcp-templates.md)

package/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "4.19.0",
+  "version": "4.20.0",
   "components": {
     "agents": {
       "description": "44 specialized agents (orchestrator, backend, frontend, security, devops, etc.)",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@softspark/ai-toolkit",
-  "version": "4.19.0",
+  "version": "4.20.0",
   "description": "AI coding toolkit: 108 skills, 44 agents, 12 developer-tool integrations, recoverable native tool-output filtering, Claude Chat/Cowork export, safety constitution, SARIF audit, and signed npm provenance.",
   "keywords": [
     "claude",
@@ -34,7 +34,7 @@
   "bugs": {
     "url": "https://github.com/softspark/ai-toolkit/issues"
   },
-  "license": "MIT",
+  "license": "Apache-2.0",
   "author": "SoftSpark <biuro@softspark.eu>",
   "main": "bin/ai-toolkit.js",
   "bin": {
@@ -88,6 +88,7 @@
     "README.md",
     "CHANGELOG.md",
     "LICENSE",
+    "NOTICE",
     "AGENTS.md",
     "llms.txt",
     "llms-full.txt"

package/scripts/_common.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Shared library for ai-toolkit Python scripts.
 
 This module is a **facade** that re-exports from focused sub-modules:

package/scripts/add_rule.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """add-rule -- Register a rule file or URL in ~/.softspark/ai-toolkit/rules/.
 
 Registered rules are automatically injected into all AI tool configs

package/scripts/audit_skills.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Skill & Agent Security Auditor.
 
 Deterministic scanner for ai-toolkit skills and agents.

package/scripts/benchmark_config.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """ai-toolkit benchmark --my-config — Compare user config vs toolkit vs ecosystem."""
 from __future__ import annotations
 

package/scripts/benchmark_ecosystem.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """benchmark-ecosystem — Generate ecosystem benchmark snapshot.
 
 Usage:

package/scripts/check_deps.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Check required dependencies and tell the user what to install.
 
 Detects OS/distro and provides ready-to-copy install commands.

package/scripts/claude_app.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Build and verify the uploadable ai-toolkit plugin for the Claude app.
 
 Claude Code reads ``~/.claude`` directly. Claude Chat and Cowork do not: they

package/scripts/codex_skill_adapter.py

@@ -1,3 +1,7 @@
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Adapt ai-toolkit skills for Codex CLI.
 
 Compatible skills are symlinked as-is. Skills that rely on Claude-only

package/scripts/compile_slm.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Compile ai-toolkit into a minimal system prompt for Small Language Models.
 
 Reads all toolkit components (constitution, agents, skills, rules, personas),

package/scripts/config_cli.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """CLI dispatcher for ai-toolkit config subcommands.
 
 Usage:

package/scripts/config_lock.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Lock file management for ai-toolkit config inheritance.
 
 Generates and consumes .softspark-toolkit.lock.json for reproducible

package/scripts/config_merger.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Config merger for ai-toolkit extends system.
 
 Implements layered deep merge with:

package/scripts/config_resolver.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Config resolver for ai-toolkit extends system.
 
 Resolves base configs from npm packages, git URLs, or local paths.

package/scripts/config_scaffold.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Scaffolding for ai-toolkit config inheritance.
 
 - create_base_package(): Scaffold an npm base config package
@@ -177,7 +181,7 @@ Use the `enforce` block to set non-overridable constraints:
     "minHookProfile": "standard",
     "requiredAgents": ["security-auditor"],
     "forbidOverride": ["constitution"],
-    "requiredPlugins": ["security-pack"]
+    "requiredPlugins": ["memory-pack"]
   }}
 }}
 ```

package/scripts/config_validator.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Config validator for ai-toolkit extends system.
 
 Validates .softspark-toolkit.json against schema, checks enforce constraints,

package/scripts/create_skill.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """ai-toolkit create skill -- Scaffold a new skill from a template.
 
 Usage:

package/scripts/dir_rules_shared.py

@@ -1,3 +1,7 @@
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Shared content and helpers for directory-based rule generators.
 
 Used by: Antigravity, Cursor .mdc, Windsurf, Cline, Roo Code.

package/scripts/doctor.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """ai-toolkit doctor -- Installation health and configuration diagnostics.
 
 Checks:

package/scripts/ecosystem_doctor.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Ecosystem Doctor — detects upstream drift across supported tools.
 
 Reads scripts/ecosystem_tools.json, probes each tool's documentation page

package/scripts/eject.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """ai-toolkit eject -- Export standalone toolkit config.
 
 Creates a self-contained copy of the toolkit configuration in the

package/scripts/emission.py

@@ -1,3 +1,7 @@
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Markdown emission helpers for agent/skill listing and generator content blocks.
 
 Provides functions to emit agents and skills as markdown headings or

package/scripts/evaluate_skills.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """AI Toolkit Skill Evaluation.
 
 Validates all skills against the Agent Skills standard.

package/scripts/frontmatter.py

@@ -1,3 +1,7 @@
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """YAML frontmatter parsing for agent and skill markdown files.
 
 Stdlib-only. Extracts fields from ``---`` delimited frontmatter blocks.

package/scripts/generate_agents_md.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate the shared AGENTS.md instruction core.
 
 Output is compatible with the Codex and GitHub Copilot AGENTS.md format.

package/scripts/generate_aider_conf.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate .aider.conf.yml configuration.
 
 Usage: ./scripts/generate_aider_conf.py > .aider.conf.yml

package/scripts/generate_antigravity.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate Antigravity IDE ``.agents/rules/``, ``.agents/workflows/``, and
 skill pointer files.
 

package/scripts/generate_augment.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate Augment AI rules from app/agents/*.md and app/skills/*/SKILL.md.
 
 Augment uses ~/.augment/rules/*.md (user-level, always_apply) or

package/scripts/generate_augment_agents.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate ``.augment/agents/ai-toolkit-*.md`` files for Augment Code.
 
 Each ai-toolkit agent in ``app/agents/`` is mirrored as an Augment native

package/scripts/generate_augment_commands.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate ``.augment/commands/ai-toolkit-*.md`` files for Augment Code.
 
 User-invocable skills become Augment custom slash commands. Knowledge skills

package/scripts/generate_augment_hooks.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate Augment settings.json hooks block.
 
 Augment reads hooks from several settings.json layers (per

package/scripts/generate_augment_rules.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate .augment/rules/ai-toolkit-*.md files for Augment Code.
 
 Augment supports per-file rules with frontmatter:

package/scripts/generate_augment_skills.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate an Augment skill pointer under ``.augment/skills/``.
 
 Augment's SKILL.md reader follows the Agent Skills standard at

package/scripts/generate_cline.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate .clinerules from app/agents/*.md and app/skills/*/SKILL.md.
 
 Usage: ./scripts/generate_cline.py > .clinerules

package/scripts/generate_cline_rules.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate ``.clinerules/*.md`` files and companion workflows for Cline.
 
 Cline reads rules from the ``.clinerules/`` directory (since Cline 3.7).

package/scripts/generate_cline_skills.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate a Cline skill pointer under ``.cline/skills/``."""
 from __future__ import annotations
 

package/scripts/generate_codex.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate the compact shared AGENTS.md policy for OpenAI Codex CLI.
 
 Agent and skill discovery is installed separately in native directories, so

package/scripts/generate_codex_agents.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate native Codex custom-agent TOML files."""
 
 from __future__ import annotations

package/scripts/generate_codex_hooks.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate native, self-contained Codex hooks without bypassing trust.
 
 Project installs write ``.codex/hooks.json`` and executable assets under

package/scripts/generate_codex_skills.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Mirror the ai-toolkit skill catalogue into Codex ``.agents/skills/``.
 
 OpenAI Codex CLI discovers Agent Skills from ``.agents/skills/`` in the

package/scripts/generate_conventions.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate CONVENTIONS.md for Aider.
 
 Aider automatically loads CONVENTIONS.md from the project root as

package/scripts/generate_copilot.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate GitHub Copilot customization files.
 
 This generator produces five repository customization surfaces without

package/scripts/generate_copilot_hooks.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate native, self-contained GitHub Copilot hooks.
 
 Repository installs write ``.github/hooks/ai-toolkit.json`` plus a managed

package/scripts/generate_cursor_agents.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate ``.cursor/agents/ai-toolkit-*.md`` files for Cursor IDE.
 
 Each ai-toolkit agent is mirrored as a Cursor custom agent. Per Cursor's

package/scripts/generate_cursor_hooks.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate native, self-contained Cursor hooks.
 
 Repository installs write ``.cursor/hooks.json`` and a managed Python runtime

package/scripts/generate_cursor_mdc.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate ``.cursor/rules/*.mdc`` files for Cursor IDE.
 
 Cursor reads rules from ``.cursor/rules/`` (since Cursor 0.45). Only ``.mdc``

package/scripts/generate_cursor_rules.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate .cursorrules from app/agents/*.md and app/skills/*/SKILL.md.
 
 Usage: ./scripts/generate_cursor_rules.py > .cursorrules

package/scripts/generate_cursor_skills.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate a Cursor skill pointer under ``.cursor/skills/``."""
 from __future__ import annotations
 

package/scripts/generate_devin_hooks.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate ``.devin/hooks.v1.json`` for the Devin CLI (formerly Windsurf).
 
 Devin CLI uses a hook format **compatible with Claude Code hooks**

package/scripts/generate_gemini.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate GEMINI.md from app/agents/*.md and app/skills/*/SKILL.md.
 
 Usage: ./scripts/generate_gemini.py > GEMINI.md

package/scripts/generate_gemini_commands.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate ``.gemini/commands/ai-toolkit-*.toml`` files for Gemini CLI.
 
 User-invocable skills become Gemini custom slash commands. Knowledge skills

package/scripts/generate_gemini_hooks.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate .gemini/settings.json hooks block for Gemini CLI.
 
 Merges ai-toolkit hook entries into `<target>/.gemini/settings.json`. User

package/scripts/generate_gemini_skills.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate a Gemini CLI skill pointer under ``.gemini/skills/``.
 
 Gemini supports the Agent Skills standard via

package/scripts/generate_language_rules_skills.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate language-rules knowledge skills from app/rules/<lang>/*.md.
 
 Each language directory under ``app/rules/`` (except ``common/``) is compiled

package/scripts/generate_llms_txt.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate llms.txt and llms-full.txt from kb/ docs.
 
 Usage:

package/scripts/generate_opencode.py

@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2024-2026 Lukasz Krzemien (biuro@softspark.eu)
+# Source: https://github.com/softspark/ai-toolkit
+
 """Generate AGENTS.md content for opencode (https://opencode.ai).
 
 opencode reads AGENTS.md using the same convention as OpenAI Codex CLI.