tdimino/claude-code-minoan

Profil tdimino

Dernière activité source enregistrée: 19 octobre 2026 à 21:44

Catalogue SkillsMP mis à jour: 26 octobre 2026 à 11:37

skills collectés: 99

Étoiles GitHub: 41
Forks GitHub: 4

README du dépôt

Fichier source du README : README.md

Lire le README source

Afficher le README complet

<img src="public/images/tanit.svg" alt="Symbol of Tanit" width="160"/> <a href="#available-skills"><img src="https://img.shields.io/badge/Skills-97-green.svg" alt="Skills"></a> <a href="commands/README.md"><img src="https://img.shields.io/badge/Commands-21-purple.svg" alt="Commands"></a> <a href="hooks/README.md"><img src="https://img.shields.io/badge/Hooks-50-orange.svg" alt="Hooks"></a> # Minoan Claude Code Configuration A curated `~/.claude/` configuration for professional development workflows — skills, hooks, CLI tools, slash commands, and MCP servers. <img src="public/images/be_minoan.jpg" alt="Minoan fresco" width="600"/> ## Repository Map ``` claude-code-minoan/ ├── skills/ # 97 custom skills across 5 categories │ ├── core-development/ # Architecture, task tracking, code search │ ├── integration-automation/ # Local ML, RAG, browser, telephony │ ├── design-media/ # Frontend, image gen, TTS, vision │ ├── research/ # Academic, web search, scraping │ └── planning-productivity/ # Session tracking, swarms, iteration loops ├── hooks/ # 50 lifecycle hooks (handoffs, terminal UX, lint-on-write, phase-detect, mycelium) ├── commands/ # 21 slash commands (session tracking, checkpoints, quotes, design, soul, workflows) ├── agents/ # Custom subagents (librarian, etc.) ├── scripts/ # Standalone utilities (syspeek, screenshot-rename, plugins) ├── bin/ # CLI tools (session tracker, launchers, tmux) ├── lib/ # Shared libraries (tracker-utils.js, tracker-db.js) ├── ghostty/ # Ghostty terminal config for Claude Code ├── sounds/ # Notification audio ├── demos/ # Complete project demos (Project Thorn, Crypt Librarian) ├── docs/windows-setup/ # Windows setup guide, PowerShell installer, Codex CLI └── docs/global-setup/ # Full ~/.claude/ structure reference ``` Each folder has its own README with setup instructions, examples, and credits. ## Quick Start ```bash # 1. Clone git clone https://github.com/tdimino/claude-code-minoan.git cd claude-code-minoan # 2. Start with the global CLAUDE.md template cp CLAUDE.template.md ~/.claude/CLAUDE.md # Edit ~/.claude/CLAUDE.md — add your Identity section, uncomment Always Loaded refs # 3. Install skills cp -r skills/*/* ~/.claude/skills/ # 4. Install commands cp -r commands/* ~/.claude/commands/ # 5. Install hooks + sounds cp -r hooks/* ~/.claude/hooks/ cp -r sounds ~/.claude/sounds/ chmod +x ~/.claude/hooks/*.py ~/.claude/hooks/*.sh # 6. Install CLI tools cp bin/* ~/.local/bin/ mkdir -p ~/.claude/lib && cp lib/* ~/.claude/lib/ ``` Configure hooks in `~/.claude/settings.json` — see [hooks/README.md](hooks/README.md) for the full settings block. **On Windows?** See the [Windows setup guide](docs/windows-setup/README.md) — includes a PowerShell installer, compatibility matrix, and [Codex CLI](docs/windows-setup/CODEX-CLI.md) setup. --- ## Deep Dives ### [Skills](skills/README.md) — 97 skills across 5 categories Custom Claude Code capabilities organized by domain. Each skill has a `SKILL.md` entry point, optional scripts, and reference docs. **Highlights**: | Category | Count | Notable Skills | |----------|-------|---------------| | Core Development | 15 | `fable`, `skill-optimizer`, `claude-agent-sdk`, `claude-md-manager`, `dag-typesafe`, `glossary`, `autoresearch`, `claude-usage`, `architecture-md-builder`, `stop-slop`, `test-harness-auditor`, `user-model-builder` | | Integration & Automation | 31 | `opencli`, `cloudflare`, `rlama`, `llama-cpp`, `slack`, `sms`, `telegram`, `mycelium`, `open-interpreter`, `codex-orchestrator` (parallel-safe personas), `obscura`, `stock-monitor` | | Design & Media | 33 | `minoan-frontend-design` (70% win rate), `scroll-cinema`, `conductor-motion`, `vellum-editorial`, `gpt-atelier`, `nano-banana-pro`, `gemini-forge`, `sprite-forge` (Retro Diffusion + fal genmedia, pipeline profiles), `image-well`, `image-forge`, `paper-design`, `pretext`, `shadcn`, `meshy`, `particle-swarm-sim`, `tamarru` | | Research | 10 | `omnisearch`, `geo-seo`, `academic-research`, `ancient-near-east-research`, `exa-search`, `firecrawl`, `keenable`, `scrapling`, `openplanter`, `reverse-trace` | | Planning & Productivity | 8 | `minoan-swarm`, `skill-toggle`, `super-ralph-wiggum`, `claude-tracker-suite` (FTS5 transcript search, title/nickname history, fzf picker, checkpoints, workflow phases, tagged phrases, workspace save/restore, cost tracking via optional SQLite), `codex-tracker-suite` (native App Server search, inspection, status, and safe resume commands), `travel-requirements-expert` | Toggle skills on/off: `python3 ~/.claude/skills/skill-toggle/scripts/skill_toggle.py list` **Parallel-safe Codex personas**: `codex-orchestrator` passes each role through per-invocation `developer_instructions` while leaving Codex's global, repository, and nested `AGENTS.md` chain untouched. Independent read-only agents can fan out immediately; agents that write overlapping files should still run serially or in separate worktrees. **Codex argv hygiene (2026-09-19)**: `codex exec -i/--image` is variadic, so the launchers now emit it after `resume` and terminate options with `--` before the prompt; captured-output profiles print Codex's own diagnostics when a run yields nothing. Codex CLI 0.155.x did not change PTY or prompt handling. > **Claude 4.6 Prompting Alignment (Feb 2026)**: All agentic skills (`minoan-swarm`, `super-ralph-wiggum`, `firecrawl`, `claude-agent-sdk`, `skill-optimizer`) updated to follow [Anthropic's Claude 4.6 prompting best practices](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices)—softer tool-use language, factual quality criteria over motivational framing, effort parameter guidance, structured state management. --- **Memory Hierarchy**: The `claude-md-manager` skill documents the full [6-tier memory system](skills/core-development/claude-md-manager/references/memory-hierarchy.md) — managed policy, project memory, project rules (`.claude/rules/`), user memory, project local, and auto memory. See also `docs/global-setup/README.md` for how this complements the [Claudicle](https://github.com/tdimino/claudicle) soul architecture. --- ### [Hooks](hooks/README.md) — 50 lifecycle event scripts 30 Python + 20 Bash scripts across 10 lifecycle events. Highlights: ``` PreToolUse ────────→ git-track.sh (log git commands to JSONL) → image-optimize.py (auto-resize images, PNG→JPEG) PostToolUse ───────→ lint-on-write.py (ESLint/Clippy/Ruff + custom rules) → phase-detect.py (detect workflow phase transitions) PermissionRequest ─→ smart-auto-approve.py (auto-approve safe read-only commands) Stop ──────────────→ session-tags-infer.py (AI-powered session tagging) PreCompact/End ────→ precompact-handoff.py (structured YAML handoff for context survival) SessionStart ──────→ soul-activate.py (register Claudicle soul) SubagentStart ─────→ soul-subagent-inject.py (inject soul into subagents) ``` See [hooks/README.md](hooks/README.md) for the full event map, hook dependencies, and settings.json configuration. **Terminal Title**: Two-tier format with repo-type emoji icons — `🔴 🐍 claudicle: Building test suite`. Icons auto-detected from CLAUDE.md keywords and project files. Main title persists across events; subtitle updates from transcript. **Session Handoff System**: Three hooks ensure context survives compaction, graceful exits, and crashes. Writes structured YAML to `~/.claude/handoffs/` with objective, decisions, blockers, and next steps. Auto-maintains `INDEX.md`. **Git Tracking**: Three hooks intercept git commands across any directory, capturing repos, branches, operations, and commit hashes. Builds a bidirectional session↔repo index. Query with `getSessionsForRepo()` / `getReposForSession()` or generate a dashboard with `/session-report`. **Plan Auto-Naming**: Renames randomly-named plan files (e.g. `tingly-humming-simon.md`) to dated slugs (e.g. `2026-02-17-auto-rename-plan-files-hook.md`) by extracting the H1 header. Creates forwarding symlinks for mid-session continuity; cleaned up on SessionEnd. **Session Auto-Titling**: When a plan file is created, `plan-session-rename.py` immediately extracts the H1 header and injects a `custom-title` event into the session's JSONL transcript—no LLM call, pure local, ~10ms. Claude Code's resume picker reads it from there, and `session-sync-db.py` mirrors it into `tracker.db` on the next Stop. **Lint-Directed Agent Loop**: `lint-on-write.py` runs standard linters (ESLint, Clippy, Ruff) and custom grep-based convention rules after every Write/Edit, returning violations as `additionalContext` so the agent self-corrects against machine-enforced rules. Any repo can opt in by dropping a `.claude/lint-rules.json` config file declaring which linter to use and what CLAUDE.md conventions to enforce as grep rules. Implements the [Factory.ai pattern](https://factory.ai/news/using-linters-to-direct-agents). 5s per-file cooldown, 10-violation cap. --- ### [Commands](commands/README.md) — 16 slash commands Markdown templates invoked as `/command-name`. Key workflows: | Command | Purpose | |---------|---------| | `/requirements-start` | Structured project planning through discovery questions | | `/workflows:review` | 12+ parallel agent code review | | `/code-review` | PR review with structured output | | `/audit-plans` | Plan completeness auditing | | `/workflows:plan` | Transform descriptions into implementation plans | | `/session-report` | Markdown dashboard: sessions, git activity, commits, repos | --- ### [Agents](agents/) — Custom subagents Read-only research subagents invoked via the Task tool with `subagent_type: "Bash"` and the agent instructions in the prompt. | Agent | Model | Purpose | |-------|-------|---------| | `fable` | fable | Naos (ναός, √n-w-y)—visiting Mythos-class spirit for long-horizon tasks; `--opus` runs Opus 5 at half cost. 100-turn budget, full tool access, model self-report verification. Availability probed at invocation—permanent subscription access since July 2026, probe errors never reroute to Opus. | | `librarian` | sonnet | GitHub repo exploration via `gh` CLI. Caches to `/tmp/claude-librarian/`. | --- ### [CLI Tools](bin/README.md) — Session management & launchers | Tool | Purpose | |------|---------| | `claude-tracker` | List recent sessions with LIVE/INACTIVE status from Claude Code's PID files | | `claude-tracker-search` | FTS5 transcript search (index refreshed on every search, sessions from today included) | | `claude-tracker-recent` | Recent sessions straight from `tracker.db`—the fast listing | | `claude-tracker-alive` | Live vs. stale sessions (`--json`, `--stale`, `--all-kinds`) | | `claude-tracker-resume` | Find crashed sessions and reopen them in Ghostty tabs (`--open`, `--workspace`) | | `ghostty-resume.sh` | The one terminal opener: session ID → new Ghostty tab or split (`--split right`) | | `claude-tmux-status` | Tmux statusline integration for session info | | `cc` / `cckill` / `ccls` / `ccpick` | Quick launchers and session management | | `ccnew` | Start a new session in a Ghostty tab (`--name`, `--model`, `--prompt`, `--headless`) | All CLIs are thin wrappers over `skills/planning-productivity/claude-tracker-suite/scripts/` and share `lib/tracker-utils.js` (session parsing, live detection) and `lib/tracker-db.js` (Node's built-in `node:sqlite`, no npm dependency). Ghostty is the only terminal target; cmux, tmux, Terminal.app and VS Code resume paths are retired. On Ghostty ≥ 1.3 the opener drives the native AppleScript dictionary (no keystrokes, no clipboard); older builds fall back to Cmd-T plus a single paste. ### Session Cost Tracking The enrichment pipeline (`parseSessionEnriched` in `lib/tracker-utils.js`) scans full JSONL transcripts to aggregate token usage from every API call, then computes USD cost using Anthropic's published per-model pricing. ```bash sqlite3 ~/.claude/tracker.db "SELECT short_id, num_turns, printf('\$%.2f', total_cost_usd), model_short FROM sessions ORDER BY total_cost_usd DESC LIMIT 10;" ``` --- ### [Plugin Profile Manager](scripts/claude-plugins.py) — `cplugins` Claude Code has an undocumented [~37-40 agent limit](https://github.com/anthropics/claude-code/issues/18993). When total agents (built-in + plugin + custom) exceed this, agents are silently dropped with no warning. This tool manages plugin profiles to keep the total under the limit. ```bash cplugins status # Show current profile, agent counts, over/under limit cplugins soul # All custom subdaimones, no compound-engineering (34 agents) cplugins compound # Compound Engineering workflows (45 agents) cplugins lean # Maximum headroom, minimal plugins (17 agents) cplugins --only compound-engineering model-trainer # Ad-hoc: enable only these ``` **Setup**: ```bash cp scripts/claude-plugins.py ~/.claude/scripts/ cp scripts/plugin-profiles.json ~/.claude/scripts/ chmod +x ~/.claude/scripts/claude-plugins.py echo "alias cplugins='python3 ~/.claude/scripts/claude-plugins.py'" >> ~/.zshrc ``` Profiles are defined in `plugin-profiles.json`. Edit `AGENT_COUNTS` in the script when plugins change. Changes take effect on next session start. --- ### [Global Config Reference](docs/global-setup/README.md) — Full `~/.claude/` structure Complete reference for the `~/.claude/` directory: CLAUDE.md patterns, user persona models, progressive disclosure with `agent_docs/`, settings.json hooks/MCP/plugins, session handoff system, plans, and design principles. --- ## Recommended Plugins ### `feature-dev` — Claude Code Team's Arsenal The official plugin from the Claude Code team: ```bash /plugin marketplace add anthropics/claude-code /plugin install feature-dev ``` Three specialized agents: `code-architect` (implementation blueprints), `code-explorer` (trace execution paths), `code-reviewer` (confidence-based review). ### `compound-engineering` — Multi-Agent Review Workflows By [Every AI Labs](https://github.com/every-ai-labs/compound-engineering). Provides 12+ specialized review agents (security-sentinel, performance-oracle, architecture-strategist, etc.) and workflow orchestration commands. --- ## MCP Servers > We've shifted toward skills over MCPs for most workflows. Claude Code's [MCP Tool Search](https://www.atcyrus.com/stories/mcp-tool-search-claude-code-context-pollution-guide) loads tools on-demand, reducing context pollution by ~85%. Configured in `.mcp.json`: supabase, playwright, context7, shadcn, figma, arxiv, perplexity, telnyx, twilio, and more. See the file for full configuration. --- ## [Ghostty Config](ghostty/README.md) — Terminal for Claude Code Optimized [Ghostty](https://ghostty.org/) config: Catppuccin Mocha/Latte theme, JetBrainsMono Nerd Font with codepoint maps for Linear A/B, Phaistos Disc, and Minoan Glyphs (PUA), 100K scrollback, split panes for parallel sessions, prompt jumping, and session persistence. ```bash brew install --cask font-jetbrains-mono-nerd-font cp ghostty/config ~/Library/Application\ Support/com.mitchellh.ghostty/config ``` Key bindings: `Cmd+D` split right, `Cmd+Alt+Enter` zoom split, `Cmd+Up/Down` jump prompts. See [ghostty/README.md](ghostty/README.md) for full keybinding reference. Pair with **ccstatusline** (`npm install -g ccstatusline`) and **lazygit** (`brew install lazygit`) in a side split. --- ## Teammate Onboarding **Start here**: Read [`ARCHITECTURE.md`](ARCHITECTURE.md) for a bird's-eye view of the repo structure, then follow the steps below. **[`CLAUDE.template.md`](CLAUDE.template.md)** — A teammate-ready global config with all tooling conventions and no personal details. ```bash cp CLAUDE.template.md ~/.claude/CLAUDE.md cp -r docs/global-setup/agent_docs/*.md ~/.claude/agent_docs/ ``` Then customize: - **Identity**: Create `~/.claude/userModels/{yourname}/{yourname}Model.md` and uncomment the `@reference`. See the [userModel guide](docs/guides/usermodel-guide.md). - **Always Loaded**: Uncomment `@agent_docs/` references you want active in every session. See [progressive disclosure](docs/guides/progressive-disclosure.md). - **On-Demand References**: Add paths to docs Claude should read when relevant - **Agent docs**: The starter templates in `docs/global-setup/agent_docs/` give you active-projects, skills inventory, tools reference, and MCP server docs to customize. See [`docs/global-setup/README.md`](docs/global-setup/README.md) for the full `~/.claude/` structure reference, including userModel examples. The template includes: engineering principles, tool preferences (firecrawl, uv, RLAMA retrieve-only default), interaction conventions, planning patterns, and infrastructure notes. --- ## Contributing 1. **Skills**: Follow the `SKILL.md` + `scripts/` + `references/` structure. Test across projects. 2. **Commands**: Use frontmatter (`description`, `argument-hint`). Keep single-purpose. 3. **Hooks**: Test with piped JSON input before wiring into `settings.json`. --- ## Companion Projects ### [Claudicle](https://github.com/tdimino/claudicle) — Soul Agent Framework Open-source 4-layer soul architecture (Identity, Cognition, Memory, Channels) that gives Claude Code sessions persistent personality, memory, and behavioral continuity. The soul hooks in this repo (`soul-activate.py`, `soul-deregister.py`, `soul-registry.py`) register sessions with the Claudicle daemon. Souls like Kothar—the Ugaritic craftsman god—maintain identity across sessions, respond on Slack, and dream in the Daimon Chamber. ```bash git clone https://github.com/tdimino/claudicle cd claudicle && ./setup.sh --personal # then in any Claude Code session: /ensoul ``` ### [Dabarat](https://github.com/tdimino/dabarat) — Live Markdown Preview AI-native markdown previewer with annotations, bookmarks, and live reload. Zero dependencies. The `dabarat-open.py` hook auto-opens new `.md` files in a browser tab as Claude writes them—plans, docs, and READMEs render live. Multi-tab support, margin annotations, and global bookmarks saved to `~/.claude/bookmarks/`. ```bash git clone https://github.com/tdimino/dabarat cd dabarat && pip install -e . dabarat plan.md # preview in browser dabarat --add spec.md # add tab to running instance ``` ### [ClipLog](https://github.com/tdimino/cliplog) — Clipboard History Daemon Git-tracked clipboard history with source attribution for macOS. Polls `NSPasteboard` every 500ms, logs to daily JSONL files at `~/.clipboard-log/`, and tags each copy with the frontmost application. Distinguishes `claude` copies (Terminal, Ghostty, VS Code) from `user` copies (Safari, Finder). Auto-redacts API keys and secrets. Auto-commits on shutdown and midnight rollover. ```bash git clone https://github.com/tdimino/cliplog cd cliplog && uv sync uv run python cliplog.py # run daemon uv run python cliplog_query.py today --source claude # query Claude copies uv run python cliplog_query.py today --table # box-drawing table output uv run python cliplog_query.py search "function" # full-text search uv run python cliplog_query.py stats # per-app breakdown ``` Persistent daemon via launchd: `cp com.minoan.cliplog.plist ~/Library/LaunchAgents/ && launchctl load ~/Library/LaunchAgents/com.minoan.cliplog.plist` ### [claude-peers](https://github.com/tdimino/claude-peers-mcp) — Claude ↔ Codex Messaging Claude Code and Codex CLI sessions on one machine message each other through a launchd broker. Instead of relying on polling, the broker wakes the recipient through Claude Code's inbox socket or `codex queue`, and a `Stop`/`PreToolUse` hook catches any missed wake. Use native `SendMessage` for Claude-to-Claude. Setup: [`skills/integration-automation/claude-peers/`](skills/integration-automation/claude-peers/README.md). --- ## Credits & Inspiration - **[Claude Code](https://github.com/anthropics/claude-code)** by Anthropic — the terminal-first AI coding tool - **[Open Souls](https://github.com/opensouls/opensouls)** — the AI souls paradigm - **[compound-engineering](https://github.com/every-ai-labs/compound-engineering)** by Every AI Labs — multi-agent review workflows - **[feature-dev plugin](https://github.com/anthropics/claude-code)** by the Claude Code team — code-architect, code-explorer, code-reviewer - **[super-ralph-wiggum](https://www.aihero.dev/tips-for-ai-coding-with-ralph-wiggum)** by AI Hero — autonomous iteration loop pattern - **[ccstatusline](https://github.com/sirmalloc/ccstatusline)** by sirmalloc — terminal statusline for Claude Code - **[beautiful-mermaid](https://github.com/nicepkg/beautiful-mermaid)** by Craft — Mermaid diagram rendering - **[llama.cpp](https://github.com/ggerganov/llama.cpp)** by Georgi Gerganov — local LLM inference - **[RLAMA](https://github.com/dontizi/rlama)** by dontizi — local RAG system - **[Firecrawl](https://firecrawl.dev/)** by Mendable — web scraping and content extraction - **[Scrapling](https://github.com/D4Vinci/Scrapling)** by D4Vinci — local stealth web scraping - **[Exa](https://exa.ai/)** — web search and Agent API - **[Handy](https://github.com/cjpais/Handy)** by CJ Pais — push-to-talk speech-to-text - **[matklad's ARCHITECTURE.md](https://matklad.github.io/2021/02/06/ARCHITECTURE.md.html)** — codebase documentation guide --- **Skills**: 97 | **Commands**: 21 | **Hooks**: 50 | **CLI Tools**: 10 --- *"ἀπιστίῃ διαφυγγάνει μὴ γιγνώσκεσθαι."* — "Divine things escape recognition through disbelief." — Heraclitus

Chargement du README du dépôt…

Skills dans ce dépôt

Développeurs de logiciels Développeurs web Graphistes Administrateurs de réseaux et de systèmes informatiques

18 catégories métier · 88% classifié

skill

métier

description

mis à jour

academic-research

non classé

Search academic papers, build literature reviews, and synthesize research findings — combines Exa search (publication category, domain and date filters) with arxiv-mcp-server for paper discovery, download, and deep analysis. Triggers on academic paper,…