@softspark/ai-toolkit 1.6.1 → 1.7.0

package/CHANGELOG.md

@@ -7,6 +7,21 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 
 ---
 
+## v1.7.0 — Offline-First SLM Compilation (2026-04-11)
+
+### Added
+- **`compile-slm` command** — compiles full toolkit (20K+ tokens) into a minimal system prompt for Small Language Models (2K-16K tokens). 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. `scripts/compile_slm.py`
+- **`offline-slm` profile** — `manifest.json` profile for offline/air-gapped installs
+- **Post-compilation validator** — checks constitution presence, budget compliance, guard hooks, output sanity
+- **Integration guides** — step-by-step setup for Ollama, LM Studio, Aider, Continue.dev printed after compilation
+- **61 tests** for compile-slm (token counter, parser, compression, packer, emitter, formats, CLI, determinism, budget compliance, validator, guides)
+
+### Fixed
+- **Skill counts** — synced stale count 91 → 92 across README.md (3 locations) and manifest.json
+- **KB frontmatter validation** — `kb/history/` excluded from category-dir match (archived plans keep original category)
+
+---
+
 ## v1.6.1 — IDE Rule Format Compliance Audit (2026-04-10)
 
 ### Fixed

package/README.md

@@ -1,12 +1,12 @@
 # ai-toolkit
 
-> Professional-grade AI coding toolkit with multi-platform support. Machine-enforced safety, 91 skills, 44 agents, expanded lifecycle hooks, persona presets, experimental opt-in plugin packs, and benchmark tooling — works with Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, and Google Antigravity, ready in 60 seconds.
+> Professional-grade AI coding toolkit with multi-platform support. Machine-enforced safety, 92 skills, 44 agents, expanded lifecycle hooks, persona presets, experimental opt-in plugin packs, and benchmark tooling — works with Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, and Google Antigravity, ready in 60 seconds.
 
 [![CI](https://github.com/softspark/ai-toolkit/actions/workflows/ci.yml/badge.svg)](https://github.com/softspark/ai-toolkit/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 [![Skills](https://img.shields.io/badge/skills-92-brightgreen)](app/skills/)
 [![Agents](https://img.shields.io/badge/agents-44-blue)](app/agents/)
-[![Tests](https://img.shields.io/badge/tests-451%20passing-success)](tests/)
+[![Tests](https://img.shields.io/badge/tests-512%20passing-success)](tests/)
 
 ---
 
@@ -21,7 +21,7 @@ ai-toolkit install
 npx @softspark/ai-toolkit install
 ```
 
-**That's it.** Claude Code picks up 91 skills, 44 agents, quality hooks, and the safety constitution automatically.
+**That's it.** Claude Code picks up 92 skills, 44 agents, quality hooks, and the safety constitution automatically.
 
 ### Update
 
@@ -110,6 +110,19 @@ ai-toolkit eject /path/to    # export to custom directory
 
 Replaces all symlinks with real files, inlines rules into CLAUDE.md, copies constitution and architecture. After eject you can `npm uninstall -g @softspark/ai-toolkit`.
 
+### Compile for Local Models (Ollama, LM Studio, Aider)
+
+```bash
+ai-toolkit compile-slm                              # auto-detect model, default budget
+ai-toolkit compile-slm --model-size 8b              # 2K token budget for 8B models
+ai-toolkit compile-slm --model-size 32b --lang python  # 8K budget + Python rules
+ai-toolkit compile-slm --persona backend-lead       # boost backend-relevant skills
+ai-toolkit compile-slm --format ollama              # Ollama Modelfile SYSTEM block
+ai-toolkit compile-slm --dry-run                    # preview what gets included
+```
+
+Compiles the full toolkit (20K+ tokens) into a minimal system prompt that fits SLM context windows. Preserves safety constitution, compresses skills, and packs by value density. Supports 4 output formats: `raw`, `ollama`, `json-string`, `aider`.
+
 ---
 
 ## Platform Support
@@ -159,7 +172,7 @@ ai-toolkit/
 │   │   ├── backend-specialist.md
 │   │   ├── security-architect.md
 │   │   └── ... (41 more)
-│   ├── skills/          # 91 skills (task / hybrid / knowledge)
+│   ├── skills/          # 92 skills (task / hybrid / knowledge)
 │   │   ├── commit/      # /commit slash command
 │   │   ├── review/      # /review slash command
 │   │   ├── clean-code/  # knowledge skill (auto-loaded)

package/app/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "ai-toolkit",
   "description": "Professional-grade Claude Code toolkit with persona presets, skill security auditor, expanded lifecycle hooks, experimental opt-in plugin packs, benchmark harvesting, and multi-tool support.",
-  "version": "1.6.1",
+  "version": "1.7.0",
   "author": {
     "name": "SoftSpark",
     "url": "https://github.com/softspark"

package/app/ARCHITECTURE.md

@@ -312,6 +312,9 @@ Language rules are propagated to **all configured editors** — not just Claude.
 ### 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.
 
+### SLM Compilation (`compile-slm`)
+`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).
+
 ### 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/bin/ai-toolkit.js

@@ -48,6 +48,7 @@ const SCRIPT_COMMANDS = {
   'benchmark-ecosystem':  { script: 'benchmark_ecosystem.py', toolkitCwd: true },
   'evaluate':             { script: 'evaluate_skills.py',    toolkitCwd: true },
   'stats':                { script: 'stats.py' },
+  'compile-slm':          { script: 'compile_slm.py' },
 };
 
 // ---------------------------------------------------------------------------
@@ -92,6 +93,7 @@ const COMMANDS = {
   'augment-dir-rules': 'Generate .augment/rules/ai-toolkit-*.md for Augment (recommended)',
   'antigravity-rules': 'Generate .agent/rules/ and .agent/workflows/ for Google Antigravity',
   'agents-md': 'Regenerate AGENTS.md from agent definitions',
+  'compile-slm': 'Compile toolkit into a minimal SLM system prompt (--budget, --model-size, --dry-run)',
   'llms-txt': 'Generate llms.txt and llms-full.txt',
   'generate-all': 'Generate all platform configs at once (agents, cursor, windsurf, copilot, gemini, cline, roo, aider, augment, antigravity, llms)',
   help: 'Show this help message',

package/kb/{planning/offline-slm-profile-plan.md → history/completed/offline-slm-profile-plan-20260411.md}

@@ -12,17 +12,19 @@ tags:
   - context-optimization
   - privacy
 doc_type: plan
-status: proposed
+status: completed
 created: "2026-04-10"
-last_updated: "2026-04-10"
-completion: "0%"
+last_updated: "2026-04-11"
+completion: "100%"
+completed: "2026-04-11"
 description: "Lightweight profile for ai-toolkit optimized for Small Language Models (SLMs) running locally via Ollama, LM Studio, or similar. Compiles a minimal instruction set that fits within 4K-8K system prompt budgets while preserving critical safety guardrails. Targets air-gapped, privacy-first, and cost-sensitive development workflows."
 ---
 
 # Plan: Offline-First SLM Profile — Lightweight Mode for Local Models
 
-**Status:** Proposed
-**Completion:** 0%
+**Status:** Completed
+**Completion:** 100%
+**Completed:** 2026-04-11
 **Created:** 2026-04-10
 **Origin:** Enterprise IP security requirements (air-gapped environments), cost-sensitive solo developers, and the growing adoption of local models (Ollama, LM Studio, llamafile). Current toolkit emits 20K+ token system prompts that exceed SLM context windows and degrade small model performance.
 **Estimated Effort:** 4-5 weeks (1 person)

package/kb/reference/architecture-overview.md

@@ -64,6 +64,7 @@ ai-toolkit/
     plugin.py                # Plugin pack management (install, remove, list, status)
     benchmark_ecosystem.py   # Generates ecosystem benchmark snapshot
     harvest_ecosystem.py     # Writes machine-readable ecosystem harvest JSON
+    compile_slm.py           # Compiles toolkit into minimal SLM system prompt (2K-16K tokens)
   tests/                     # Bats test suite
   benchmarks/                # Benchmark tasks + results
   kb/                        # Knowledge base

package/kb/reference/skills-catalog.md

@@ -260,6 +260,21 @@ depends-on: clean-code, api-patterns
 - Reported in `evaluate_skills.py` quality metrics
 - No runtime autoloading — Claude loads knowledge skills contextually based on topic matching
 
+### SLM Compilation (`compile-slm`)
+
+Compiles the full toolkit into a minimal system prompt for local Small Language Models (Ollama, LM Studio, Aider, Continue.dev). Pipeline: Parse → Score → Compress → Pack → Validate → Emit.
+
+| Flag | Purpose |
+|------|---------|
+| `--model-size` | 7b/8b/14b/32b/70b — auto-selects budget + compression level |
+| `--budget` | Token budget override (2K-16K) |
+| `--persona` | Boost persona-relevant skills in scoring |
+| `--lang` | Include language-specific rules |
+| `--format` | Output: raw, ollama, json-string, aider |
+| `--dry-run` | Preview included components + token utilization |
+
+Profile `offline-slm` in `manifest.json` — installs core only, then compiles.
+
 ### Executable Scripts (18 total, stdlib-only, JSON output)
 
 | Skill | Script | Purpose |