{
  "markdown": "# claude-damn\n\nA composable skill library and opinionated harness for\n[Claude Code](https://docs.anthropic.com/en/docs/claude-code). Ships slash\ncommands, skills, hooks, permission guards, and cost-tracking tooling that layer\non top of the\n[superpowers](https://github.com/anthropics/claude-plugins-official/tree/main/superpowers)\nplugin.\n\n<img src=\"img/home-meme.png\" alt=\"home meme\" width=\"800\">\n\n> **✅ Status:** `claude-damn` is **live** in the\n> [`anthropics/claude-plugins-community`](https://github.com/anthropics/claude-plugins-community)\n> marketplace. The published marketplace version is **v1.12.0**; the working\n> tree is at **v1.12.2**, pending the next batch sync. See `CHANGELOG.md` for\n> what's in each version.\n\nInstall:\n\n```shell\nclaude plugin marketplace add anthropics/claude-plugins-community\nclaude plugin install claude-damn@claude-community\n```\n\nSee [`ROADMAP.md`](ROADMAP.md) for what's next and\n[`CHANGELOG.md`](CHANGELOG.md) for what's landed. Design specs live in\n`docs/superpowers/{specs,plans}/`.\n\n## What's in the box\n\n### Skills (slash commands)\n\nSkills compose from four modifiers — stack them to build the workflow you need:\n\n| Modifier | What it adds                            |\n| -------- | --------------------------------------- |\n| `super`  | Brainstorm requirements first, then TDD |\n| `duper`  | Isolated git worktree                   |\n| `cat`    | Parallel subagent execution             |\n| `tdd`    | Test-driven development                 |\n\nThese combine into four skill families:\n\n- **TDD** — `/tdd`, `/tdd-cat`, `/duper-tdd`, `/duper-tdd-cat`\n- **Brainstorm + TDD** — `/super`, `/super-cat`, `/super-duper`,\n  `/super-duper-cat`\n- **Debug + Fix (fixer)** — `/fixer`, `/super-fixer`, `/super-fixer-cat`,\n  `/super-duper-fixer`, `/super-duper-fixer-cat`, `/super-duper-fixer-tdd-cat`\n- **Expert Review** — `/expert-review` through\n  `/expert-super-duper-tdd-cat-review` (14 combinatoric variants), plus\n  `/expert-final-review` (pre-merge go/no-go gate)\n\nPlus utility skills: `/atlas`, `/checkpoint-save`, `/checkpoint-resume`,\n`/check-yourself`, `/cost_`, `/cost-opt`, `/fast-pr-feedback-to-me`,\n`/fast-pr-feedback-to-others`, `/fast-pr-final-self-review`, `/learn`,\n`/legal-visual-aid`, `/listen`, `/pause`, `/proceed`, `/review`, `/sme-test`,\n`/sync`, `/task-list`, `/tesseract`, `/visual-aid`, and more.\n\nSee [`skills/README.md`](skills/README.md) for the full combinatoric table.\n\n### Harness features\n\n- **Permission guards** — granular allow/ask/deny rules in `settings.json`\n  (blocks destructive GitHub CLI operations, gates commits, protects settings\n  files)\n- **Inline-script hook** — pre-tool hook that blocks multiline non-Bash scripts\n  from running inside the Bash tool\n- **Cost tracking** — `/cost_` extracts per-session token usage from JSONL logs;\n  `/cost-opt` compacts and reviews optimization suggestions\n- **Checkpoint system** — save/resume work across sessions with automatic\n  archive rotation per branch\n- **CLAUDE.md** — opinionated project rules for model routing, testing\n  standards, Python style, and FastAPI architecture\n\n## Setup\n\n### Prerequisites\n\n- [Claude Code CLI](https://docs.anthropic.com/en/docs/claude-code) installed\n  and authenticated\n- Git\n\n### Install from the marketplace\n\n`claude-damn` is published in the\n[`anthropics/claude-plugins-community`](https://github.com/anthropics/claude-plugins-community)\nmarketplace. If you haven't already added that marketplace, do so first:\n\n```shell\nclaude plugin marketplace add anthropics/claude-plugins-community\n```\n\nThen install:\n\n```shell\nclaude plugin install claude-damn@claude-community\n```\n\nThis will register every skill, command, and the inline-script PreToolUse hook.\nRestart or reload the session once to pick up the hook.\n\nTo pull the latest published version later:\n\n```shell\nclaude plugin update claude-damn@claude-community\n```\n\n### Companion plugins\n\n`claude-damn` layers on top of `superpowers`. Install it if you don't have it\nalready:\n\n```shell\n/plugin install superpowers@claude-plugins-official\n```\n\nOther marketplace plugins the skill set composes with (all optional):\n\n| Plugin                | What it adds                 |\n| --------------------- | ---------------------------- |\n| `code-review`         | PR review workflows          |\n| `frontend-design`     | UI/UX skill                  |\n| `code-simplifier`     | Code cleanup                 |\n| `feature-dev`         | Guided feature development   |\n| `skill-creator`       | Create/edit skills           |\n| `security-guidance`   | Security audit               |\n| `pr-review-toolkit`   | Multi-agent PR review        |\n| `agent-sdk-dev`       | Agent SDK scaffolding        |\n| `hookify`             | Hook rule creation           |\n| `chrome-devtools-mcp` | Browser DevTools via MCP     |\n| `playground`          | Interactive HTML playgrounds |\n| `remember`            | Session handoff notes        |\n\n### Verify\n\nOpen a new Claude Code session and invoke any skill — e.g.:\n\n```\n/expert-review\n```\n\nThe skill content should expand in your session.\n\n### Personalize (optional)\n\nOperator-specific preferences (commit style, model routing, subagent delegation\ntargets) go in `~/.claude/rules/PERSONALIZATION.md`. Copy the template and edit\nto taste:\n\n```shell\ncp rules/PERSONALIZATION.example.md ~/.claude/rules/PERSONALIZATION.md\n```\n\n`CLAUDE.md` holds general engineering rules that apply to every clone and should\nstay in sync with upstream.\n\n### Manual install (for contributors)\n\nIf you're hacking on `claude-damn` itself, install from a local clone:\n\n```shell\ngit clone https://github.com/laurac8r/claude-damn\ncd claude-damn\nuv sync        # dev/test dependencies\nuv run pytest  # 719 tests green (777 total; smoke + performance deselected by default)\n```\n\nThen point Claude Code at the local checkout so skills, commands, and the\nPreToolUse hook load from your working tree (not the published marketplace\ncopy):\n\n```shell\nclaude --plugin-dir /absolute/path/to/claude-damn\n```\n\nOr use `--add-dir` to allow tool access without registering as a plugin:\n\n```shell\nclaude --add-dir /absolute/path/to/claude-damn\n```\n\nWhen you're done hacking, drop the local install and go back to the marketplace\ncopy:\n\n```shell\nclaude plugin install claude-damn@claude-community\n```\n\n## Quickstart\n\nA few skill invocations to get a feel for the workflow:\n\n```claude-like\n/tdd                  # Start a test-driven development loop\n/super                # Brainstorm first, then TDD\n/super-duper-cat      # Brainstorm + worktree isolation + parallel subagents\n/expert-review        # Multi-phase expert code review\n/checkpoint-save      # Save resumable work state\n/checkpoint-resume    # Pick up where you left off\n/cost_                # Log this session's token spend\n```\n\nSee [`skills/README.md`](skills/README.md) for the full combinatoric table of\nhow `super` / `duper` / `cat` / `tdd` compose into 20+ skill variants.\n\n## Project structure\n\n```tree-like\n.\n├── .claude-plugin/\n│   └── plugin.json            # Plugin manifest (name, version, author, keywords)\n├── CLAUDE.md                  # Project instructions (model routing, style, testing)\n├── README.md                  # This file\n├── LICENSE                    # MIT\n├── settings.json              # Default harness config (permissions, hooks, plugins)\n├── pyproject.toml             # Python tooling (uv, pytest, ruff, ty)\n├── skills/                    # Auto-discovered skills (one SKILL.md per skill)\n│   ├── README.md              # Full combinatoric skill table\n│   ├── tdd/                   # Base TDD workflow\n│   ├── super/                 # Brainstorm + TDD\n│   ├── duper/                 # Git worktree isolation\n│   ├── cat/                   # Subagent-driven development\n│   ├── expert-review/         # Multi-phase expert review\n│   ├── expert-*-review/       # 13 combinatoric variants + /expert-final-review gate\n│   ├── checkpoint-save/       # Save resumable checkpoint\n│   ├── checkpoint-resume/     # Resume from checkpoint\n│   ├── tesseract/             # Cross-session memory via file I/O\n│   └── ...\n├── hooks/\n│   ├── hooks.json             # PreToolUse registration\n│   └── block-inline-scripts.py # Guardrail for multiline non-Bash scripts\n├── src/\n│   └── extract_cost.py        # Token-usage parser for session JSONL logs\n├── scripts/\n│   └── statusline-command.sh  # Per-session cost in the statusline\n├── tests/                     # pytest + bats suite\n└── docs/\n    └── superpowers/           # Design specs (sme-test, sme-review, etc.)\n```\n\n## Running tests\n\nTests are organized by fidelity level. Default `uv run pytest` runs everything\nexcept `smoke` and `performance` (see `pyproject.toml` markers).\n\n| Kind        | Location             | What it checks                                          | Command                                                              |\n| ----------- | -------------------- | ------------------------------------------------------- | -------------------------------------------------------------------- |\n| Structural  | `tests/structural/`  | Files, dirs, frontmatter — cheap existence checks       | `uv run pytest tests/structural/`                                    |\n| Behavioral  | `tests/behavioral/`  | Skill body content and protocol rules                   | `uv run pytest tests/behavioral/`                                    |\n| Integration | `tests/integration/` | Repo-wide references and cross-file consistency         | `uv run pytest tests/integration/`                                   |\n| Harness     | `tests/test_*.py`    | `settings.json`, permissions, hooks, cost extraction    | `uv run pytest tests/test_*.py`                                      |\n| Bats        | `tests/*.bats`       | Shell scripts (`checkpoint-archive`, `sync-theme`)      | `bats tests/test_checkpoint_archive.bats tests/test_sync_theme.bats` |\n| Smoke       | `tests/smoke/`       | Live skill invocation (costs tokens, non-deterministic) | `uv run pytest -m smoke`                                             |\n| Performance | `tests/performance/` | Stress matrix (18 combos, expensive, non-deterministic) | `uv run pytest -m performance`                                       |\n\nRun everything cheap and deterministic:\n\n```shell\nuv run pytest\n```\n\nRun the full suite including live/expensive tests:\n\n```shell\nuv run pytest -m \"\"\n```\n\n### Parallel execution\n\nFor the slower suites (`performance/`, `smoke/`, or `-m \"\"`), run tests in\nparallel with [`pytest-xdist`](https://pytest-xdist.readthedocs.io/):\n\n```shell\nuv add --dev pytest-xdist # one-time install\nuv run pytest -n auto # auto = one worker per CPU core\nuv run pytest -n 4 -m performance # pin worker count for the 18-combo stress matrix\n```\n\nSkip `-n` for the default suite — it runs in ~0.5s, and xdist worker startup\nadds more overhead than it saves.\n\n## Privacy\n\n`claude-damn` runs entirely on your local machine. The plugin itself does not\ncollect, transmit, store, or share any user data with the author or any\nthird-party service. Specifically:\n\n- **Skills and hooks execute locally.** Every skill, every hook, every script\n  runs inside your Claude Code session on your own filesystem. Nothing is phoned\n  home to a `claude-damn` server — there is no `claude-damn` server.\n- **Cost-tracking artifacts stay on-disk.** `/cost_` writes session token-usage\n  logs to `~/.claude/cost-log/` and `~/.claude/COST-SUMMARY.md`. `/cost-opt`\n  reads and compacts those same files. None of this is uploaded anywhere.\n- **Checkpoint state stays in-repo.** `/checkpoint-save` writes `CHECKPOINT.md`\n  to your working tree and archives to `.checkpoints/` — local files only.\n- **Tesseract transmissions are local-only.** `/tesseract` reads and writes\n  `~/.tesseract/shelf/*.md` and `~/.tesseract/bulk-beings.md` on your disk. The\n  skill explicitly advises gitignoring `~/.tesseract/` entirely in any repo that\n  mirrors `~/.claude`.\n\n**Upstream data flows the plugin does not govern:**\n\n- Your prompts and Claude's responses travel to Anthropic as part of normal\n  Claude Code operation. That is governed by\n  [Anthropic's privacy policy](https://www.anthropic.com/legal/privacy), not\n  this plugin.\n- Skills that shell out to `gh`, `git`, `curl`, or other tools follow the\n  privacy practices of those tools and any remote services they talk to.\n\nIf any future version of `claude-damn` adds data collection or transmission,\nthis section will be updated before that version ships.\n\n## Bonus Track: Jetbrains Configs\n\nPrettier `Run for Files` setting:\n\n```\n**/*.{js,ts,jsx,tsx,cjs,cts,mjs,mts,json,vue,astro,md,mdx,toml,yaml,yml}\n```\n\n`Compare Files` tool canonical vs. active-dev:\n\n`!.idea/*&!projects/*&!backups/*&!cost-log/*&!cache/*&!file-history/*&!ide/*&!paste-cache/*&!plugins/*&!serena-dashboard-static/*&!session-env/*&!sessions/*&!tasks/*&!shell-snapshots/*&!telemetry/*&!security*warnings*.json*&!history.jsonl*&!settings.json*&!!tests/fixtures/settings.json*&!policy-limits.json*&!.worktrees/*&!worktrees/*&!.checkpoints/*&!.remember*&!CHECKPOINT.md*&!.claude*&!docs/superpowers*&!**pycache**/*&!*.py[cod]*&!.venv/*&!\\*.egg-info/!.idea/*&!projects/*&!backups/*&!cost-log/*&!cache/*&!file-history/*&!ide/*&!paste-cache/*&!plugins/*&!serena-dashboard-static/*&!session-env/*&!sessions/*&!tasks/*&!shell-snapshots/*&!telemetry/*&!security*warnings*.json*&!history.jsonl*&!settings.json*&!!tests/fixtures/settings.json*&!policy-limits.json*&!.worktrees/*&!worktrees/*&!.checkpoints/*&!.remember*&!CHECKPOINT.md*&!.claude*&!docs/superpowers*&!**pycache**/*&!*.py[cod]*&!.venv/*&!*.egg-info/*&!brainstorming/*&!usage-data/*!.idea/*&!projects/*&!backups/*&!cost-log/*&!cache/*&!file-history/*&!ide/*&!paste-cache/*&!plugins/*&!serena-dashboard-static/*&!session-env/*&!sessions/*&!tasks/*&!shell-snapshots/*&!telemetry/*&!security*warnings*.json*&!history.jsonl*&!settings.json*&!!tests/fixtures/settings.json*&!policy-limits.json*&!.worktrees/*&!worktrees/*&!.checkpoints/*&!.remember*&!CHECKPOINT.md*&!.claude*&!docs/superpowers*&!**pycache**/*&!*.py[cod]*&!.venv/*&!\\*.egg-info/!.idea/*&!projects/*&!backups/*&!cost-log/*&!cache/*&!file-history/*&!ide/*&!paste-cache/*&!plugins/*&!serena-dashboard-static/*&!session-env/*&!sessions/*&!tasks/*&!shell-snapshots/*&!telemetry/*&!security*warnings*.json*&!history.jsonl*&!settings.json*&!!tests/fixtures/settings.json*&!policy-limits.json*&!.worktrees/*&!worktrees/*&!.checkpoints/*&!.remember*&!CHECKPOINT.md*&!.claude*&!docs/superpowers*&!**pycache**/*&!*.py[cod]*&!.venv/*&!*.egg-info/*&!brainstorming/*&!usage-data/*&!.credentials.json`\n\n## License\n\n[MIT](LICENSE)\n",
  "bytes": 14624,
  "sha": "9138de5276a09ef15760c7577d8757d01322b8f2d4006e876ab43beba2df088a",
  "repo_slug": "laurac8r/claude-damn",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_laurac8r_claude_damn_claude_damn_27fc08ca/readme"
}