{"id":47783971,"url":"https://github.com/softspark/ai-toolkit","last_synced_at":"2026-05-04T12:05:37.147Z","repository":{"id":348685235,"uuid":"1192530919","full_name":"softspark/ai-toolkit","owner":"softspark","description":"Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI, opencode).","archived":false,"fork":false,"pushed_at":"2026-04-19T07:56:04.000Z","size":2726,"stargazers_count":137,"open_issues_count":0,"forks_count":16,"subscribers_count":5,"default_branch":"main","last_synced_at":"2026-04-19T09:33:02.270Z","etag":null,"topics":["ai-agents","ai-skills","anthropic","claude","claude-code","cline","codex","copilot","cursor","gemini","mcp","opencode","toolkit","windsurf"],"latest_commit_sha":null,"homepage":"https://softspark.eu","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/softspark.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":".github/CONTRIBUTING.md","funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null},"funding":{"github":["softspark"],"custom":["https://softspark.eu"]}},"created_at":"2026-03-26T10:02:59.000Z","updated_at":"2026-04-19T09:17:58.000Z","dependencies_parsed_at":null,"dependency_job_id":"6473df5a-0c8f-41c9-8f0e-96c5a2539bee","html_url":"https://github.com/softspark/ai-toolkit","commit_stats":null,"previous_names":["softspark/ai-toolkit"],"tags_count":30,"template":false,"template_full_name":null,"purl":"pkg:github/softspark/ai-toolkit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/softspark%2Fai-toolkit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/softspark%2Fai-toolkit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/softspark%2Fai-toolkit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/softspark%2Fai-toolkit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/softspark","download_url":"https://codeload.github.com/softspark/ai-toolkit/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/softspark%2Fai-toolkit/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32212811,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-24T03:15:14.334Z","status":"ssl_error","status_checked_at":"2026-04-24T03:15:11.608Z","response_time":64,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agents","ai-skills","anthropic","claude","claude-code","cline","codex","copilot","cursor","gemini","mcp","opencode","toolkit","windsurf"],"created_at":"2026-04-03T14:04:31.887Z","updated_at":"2026-05-04T12:05:37.140Z","avatar_url":"https://github.com/softspark.png","language":"Python","funding_links":["https://github.com/sponsors/softspark","https://softspark.eu"],"categories":[],"sub_categories":[],"readme":"# ai-toolkit\n\n\u003e Professional-grade AI coding toolkit with multi-platform support. Machine-enforced safety, 112 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, Google Antigravity, Codex CLI, and opencode, ready in 60 seconds.\n\n[![CI](https://github.com/softspark/ai-toolkit/actions/workflows/ci.yml/badge.svg)](https://github.com/softspark/ai-toolkit/actions/workflows/ci.yml)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n[![Skills](https://img.shields.io/badge/skills-112-brightgreen)](app/skills/)\n[![Agents](https://img.shields.io/badge/agents-44-blue)](app/agents/)\n[![Tests](https://img.shields.io/badge/tests-1038%20passing-success)](tests/)\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/ai-toolkit-readme-hero.png\" alt=\"ai-toolkit 3 README hero showing one toolkit for 12 AI editors\" width=\"900\"\u003e\n\u003c/p\u003e\n\n---\n\n## What's New in v3.2.1\n\nPatch release. Shellcheck cleanup of the default status line hook — no behavior change.\n\n- **Statusline lint cleanup** — `app/hooks/ai-toolkit-statusline.sh` now passes `shellcheck --severity=warning`: removed the unused `C_GRAY` color variable (SC2034) and replaced the deprecated `[ p -o q ]` form with `{ [ p ] || [ q ]; }` (SC2166).\n\nSee [CHANGELOG.md](CHANGELOG.md) for full history.\n\n---\n\n## Table of Contents\n\n- [Install](#install)\n- [Platform Support](#platform-support)\n- [What You Get](#what-you-get)\n- [Architecture](#architecture)\n- [Key Features](#key-features)\n- [Key Slash Commands](#key-slash-commands)\n- [Getting Started](#getting-started)\n- [Documentation](#documentation)\n- [Contributing](#contributing)\n- [Security](#security)\n- [License](#license)\n- [Changelog](#changelog)\n\n---\n\n## Install\n\n```bash\n# Option A: install globally (once per machine)\nnpm install -g @softspark/ai-toolkit\nai-toolkit install\n\n# Option B: try without installing (npx)\nnpx @softspark/ai-toolkit install\n```\n\n**That's it.** Claude Code picks up 112 skills, 44 agents, quality hooks, and the safety constitution automatically.\n\n**Windows:** WSL is the recommended runtime. Native Windows works when Git Bash is available for hook scripts; dependency hints cover `winget`, Chocolatey, and Scoop. See [Windows Support](kb/reference/windows-support.md).\n\n### Update\n\n```bash\nnpm install -g @softspark/ai-toolkit@latest \u0026\u0026 ai-toolkit update\n```\n\n### Per-Project Setup\n\n```bash\ncd your-project/\nai-toolkit install --local                        # Claude Code only\nai-toolkit install --local --editors all          # + all editors\nai-toolkit install --local --editors cursor,aider # + specific editors\nai-toolkit update --local                         # auto-detects editors\n```\n\n### Plugin Management\n\n```bash\nai-toolkit plugin list                            # show available packs\nai-toolkit plugin install --editor all --all      # install all for Claude + Codex\nai-toolkit plugin status --editor all             # show what's installed\n```\n\n### Install Profiles\n\n```bash\nai-toolkit install --profile minimal    # agents + skills only\nai-toolkit install --profile standard   # full install (default)\nai-toolkit install --profile strict     # full + git hooks\n```\n\n### Verify \u0026 Repair\n\n```bash\nai-toolkit validate          # check integrity\nai-toolkit doctor --fix      # auto-repair\n```\n\nSee [CLI Reference](kb/reference/cli-reference.md) for all commands and options.\n\n---\n\n## Platform Support\n\n| Platform | Config Files | Scope |\n|----------|-------------|-------|\n| Claude Code | `~/.claude/` | global |\n| Cursor | `.cursor/rules/*.mdc` + `.cursor/mcp.json` | project (`~/.cursor/mcp.json` for MCP only) |\n| Windsurf | `~/.codeium/.../global_rules.md` + `.windsurf/rules/*.md` | global + project |\n| Gemini CLI | `~/.gemini/GEMINI.md` | global |\n| GitHub Copilot | `.github/copilot-instructions.md` | project |\n| Cline | `~/Documents/Cline/Rules/*.md` + `.clinerules/*.md` | global + project |\n| Roo Code | `~/.roo/rules/*.md` + `.roomodes` + `.roo/rules/*.md` | global rules + project |\n| Aider | `~/.aider.conf.yml` + `.aider.conf.yml` + `CONVENTIONS.md` | global + project |\n| Augment | `~/.augment/rules/*.md` + `.augment/rules/ai-toolkit-*.md` | global + project |\n| Google Antigravity | `.agent/rules/*.md` + `.agent/workflows/*.md` | project |\n| Codex CLI | `AGENTS.md` + `.agents/rules/*.md` + `.agents/skills/*` + `.codex/hooks.json` | project + global plugin |\n| opencode | `AGENTS.md` + `.opencode/{agents,commands,plugins}/*` + `opencode.json` | project + global (`~/.config/opencode/`) |\n\n\u003e Claude Code is always installed (primary platform). Other editors on demand with `--editors`. All platforms receive the same agent/skill catalog, guidelines, and registered custom rules.\n\n---\n\n## What You Get\n\n| Component | Count | Description |\n|-----------|-------|-------------|\n| `skills/` (task) | 32 | Slash commands: `/commit`, `/build`, `/deploy`, `/test`, `/mcp-builder`, ... |\n| `skills/` (hybrid) | 32 | Slash commands with agent knowledge base |\n| `skills/` (knowledge) | 48 | Domain knowledge auto-loaded by agents (includes 13 `\u003clang\u003e-rules` skills) |\n| `agents/` | 44 | Specialized agents across 10 categories |\n| `hooks/` | 21 global + 5 skill-scoped | Quality gates, path safety, prompt governance, session lifecycle |\n| `plugins/` | 11 packs | Opt-in domain bundles (security, research, frontend, enterprise, 6 language packs) |\n| `constitution.md` | 6 articles | Machine-enforced safety rules |\n| `rules/` | auto-injected | Language-specific and custom rules injected into your configs |\n| `kb/` | reference docs | Architecture, procedures, and best practices |\n\n---\n\n## Architecture\n\n```\nai-toolkit/\n├── app/\n│   ├── agents/          # 44 agent definitions\n│   ├── skills/          # 112 skills (task / hybrid / knowledge)\n│   ├── rules/           # Auto-injected into your CLAUDE.md\n│   ├── hooks/           # Hook scripts (21 entries, 12 lifecycle events)\n│   ├── plugins/         # 11 experimental plugin packs (opt-in)\n│   ├── output-styles/   # System prompt output style overrides\n│   ├── constitution.md  # 6 immutable safety articles\n│   └── ARCHITECTURE.md  # Full system design\n├── kb/                  # Reference docs, procedures, plans\n├── scripts/             # Validation, install, evaluation scripts\n├── tests/               # Bats test suite (1038 tests)\n└── CHANGELOG.md\n```\n\n**Distribution:** Symlink-based for agents/skills, copy-based for hooks. Run `ai-toolkit update` after `npm install` — all projects pick up changes instantly. See [Distribution Model](kb/reference/distribution-model.md).\n\n---\n\n## Key Features\n\n**Machine-enforced constitution** — 6-article safety constitution enforced via `PreToolUse` hooks that actually block `rm -rf`, `DROP TABLE`, and irreversible operations. Not just documentation.\n\n**21 lifecycle hooks** — Executable scripts across 12 events (SessionStart → SessionEnd). Guards, governance, quality gates, session persistence, MCP health checks. See [Hooks Catalog](kb/reference/hooks-catalog.md).\n\n**Security scanning** — `/skill-audit` for code-level risks, `/cve-scan` for dependency CVEs. Both CI-ready with exit codes.\n\n**Iron Law enforcement** — `/tdd`, `debugging-tactics`, and `verification-before-completion` enforce non-negotiable gates with anti-rationalization tables. 15 skills total include rationalization resistance.\n\n**Multi-language quality gates** — `Stop` hook runs lint + type checks across Python, TypeScript, PHP, Dart, Go after every response.\n\n**Agent verification checklists** — 10 agents include exit criteria that must be met before presenting results.\n\n**Two-stage review** — `/subagent-development` runs Implementer → Spec Review → Quality Review per task.\n\n**Persistent memory** — `memory-pack` plugin: SQLite + FTS5 search across past sessions.\n\n**Local product telemetry** — `ai-toolkit stats --summary` reports total invocations, skill coverage, unused catalog skills, recent activity, and top skills from local usage data.\n\n**Persona presets** — 4 roles (backend-lead, frontend-lead, devops-eng, junior-dev) adjust style and priorities.\n\n**Config inheritance** — Enterprise `extends` system with constitution immutability and enforcement constraints. See [Enterprise Config Guide](kb/reference/enterprise-config-guide.md).\n\n**70 language rules** — 13 languages + common, 5 categories each. Auto-detected or explicit `--lang`. See [Language Rules](kb/reference/language-rules.md).\n\n**26 MCP templates** — Ready-to-use configs for GitHub, PostgreSQL, Slack, Jira, Sentry, and more. See [MCP Templates](kb/reference/mcp-templates.md).\n\nSee [Unique Features](kb/reference/unique-features.md) for detailed descriptions of all differentiators.\n\n---\n\n## Key Slash Commands\n\n| Command | Purpose | Effort |\n|---------|---------|--------|\n| `/workflow \u003ctype\u003e` | Pre-defined multi-agent workflow (15 types) | max |\n| `/orchestrate` | Custom multi-agent coordination (3–6 agents) | max |\n| `/swarm` | Parallel Agent Teams: `map-reduce`, `consensus`, `relay` | max |\n| `/plan` | Implementation plan with task breakdown | high |\n| `/review` | Code review: quality, security, performance | high |\n| `/debug` | Systematic debugging with diagnostics | medium |\n| `/refactor` | Safe refactoring with pattern analysis | high |\n| `/tdd` | Test-driven development with red-green-refactor | high |\n| `/commit` | Structured commit with linting | medium |\n| `/pr` | Pull request with generated checklist | medium |\n| `/docs` | Generate README, API docs, architecture notes | high |\n| `/explore` | Interactive codebase visualization | medium |\n| `/write-a-prd` | Create PRD through interactive interview | high |\n| `/prd-to-plan` | Convert PRD into vertical-slice implementation plan | high |\n| `/design-an-interface` | Generate 3+ radically different interface designs | high |\n| `/grill-me` | Stress-test a plan through Socratic questioning | medium |\n| `/triage-issue` | Triage bug with deep investigation and TDD fix plan | high |\n| `/architecture-audit` | Discover shallow modules, propose refactors | high |\n| `/council` | 4-perspective decision evaluation | high |\n| `/cve-scan` | Scan dependencies for known CVEs | medium |\n| `/skill-audit` | Scan skills/agents for security risks | medium |\n| `/repeat` | Autonomous loop with safety controls | medium |\n| `/persona` | Switch engineering persona at runtime | low |\n\n### `/workflow` Types\n\n```\nfeature-development    backend-feature       frontend-feature\napi-design             database-evolution    test-coverage\nsecurity-audit         codebase-onboarding   spike\ndebugging              incident-response     performance-optimization\ninfrastructure-change  application-deploy    proactive-troubleshooting\n```\n\n### Multi-Agent Skill Selection\n\n```\nNeed multi-agent coordination?\n├── Know your domains? → /orchestrate (ad-hoc, 3-6 agents)\n├── Have a known pattern? → /workflow \u003ctype\u003e (15 templates)\n├── Need consensus/map-reduce? → /swarm \u003cmode\u003e\n├── Want Agent Teams API? → /teams (experimental)\n└── Executing a plan? → /subagent-development\n```\n\n---\n\n## Getting Started\n\n1. **Customize CLAUDE.md** — add your project's tech stack, commands, and conventions at the top (above toolkit markers).\n\n2. **Start using skills:**\n   ```\n   /onboard     # guided setup interview\n   /explore     # understand your codebase\n   /plan        # plan a feature\n   ```\n\n3. **Verify your install:**\n   ```bash\n   ai-toolkit validate\n   ```\n\n---\n\n## Documentation\n\n| Topic | Link |\n|-------|------|\n| CLI Reference | [kb/reference/cli-reference.md](kb/reference/cli-reference.md) |\n| Unique Features | [kb/reference/unique-features.md](kb/reference/unique-features.md) |\n| Architecture Overview | [kb/reference/architecture-overview.md](kb/reference/architecture-overview.md) |\n| Hooks Catalog | [kb/reference/hooks-catalog.md](kb/reference/hooks-catalog.md) |\n| Language Rules | [kb/reference/language-rules.md](kb/reference/language-rules.md) |\n| MCP Templates | [kb/reference/mcp-templates.md](kb/reference/mcp-templates.md) |\n| Extension API | [kb/reference/extension-api.md](kb/reference/extension-api.md) |\n| Manifest Install | [kb/reference/manifest-install.md](kb/reference/manifest-install.md) |\n| Plugin Packs | [kb/reference/plugin-pack-conventions.md](kb/reference/plugin-pack-conventions.md) |\n| Enterprise Config | [kb/reference/enterprise-config-guide.md](kb/reference/enterprise-config-guide.md) |\n| Distribution Model | [kb/reference/distribution-model.md](kb/reference/distribution-model.md) |\n| Ecosystem Comparison | [kb/reference/comparison.md](kb/reference/comparison.md) |\n| Codex CLI Compatibility | [kb/reference/codex-cli-compatibility.md](kb/reference/codex-cli-compatibility.md) |\n| opencode Compatibility | [kb/reference/opencode-compatibility.md](kb/reference/opencode-compatibility.md) |\n| Maintenance SOP | [kb/procedures/maintenance-sop.md](kb/procedures/maintenance-sop.md) |\n\n---\n\n## Contributing\n\nSee [CONTRIBUTING.md](.github/CONTRIBUTING.md).\n\n## Security\n\nSee [SECURITY.md](SECURITY.md) for responsible disclosure policy.\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n\n## Changelog\n\nSee [CHANGELOG.md](CHANGELOG.md).\n\n---\n\n*Extracted from production use at SoftSpark. Built to be the toolkit we wished existed.*\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsoftspark%2Fai-toolkit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsoftspark%2Fai-toolkit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsoftspark%2Fai-toolkit/lists"}