{
  "markdown": "# claude-deconstruct\n\n\n<!-- mycelium-badges:start -->\n\n<p>\n  <a href=\"https://github.com/adelaidasofia/claude-deconstruct/blob/main/LICENSE\"><img alt=\"License\" src=\"https://img.shields.io/github/license/adelaidasofia/claude-deconstruct?color=blue\"></a>\n  <a href=\"https://github.com/adelaidasofia/claude-deconstruct/stargazers\"><img alt=\"GitHub stars\" src=\"https://img.shields.io/github/stars/adelaidasofia/claude-deconstruct?color=eab308\"></a>\n  <a href=\"https://github.com/adelaidasofia/claude-deconstruct/commits/main\"><img alt=\"Last commit\" src=\"https://img.shields.io/github/last-commit/adelaidasofia/claude-deconstruct\"></a>\n  <a href=\"https://github.com/adelaidasofia/claude-deconstruct/issues\"><img alt=\"Open issues\" src=\"https://img.shields.io/github/issues/adelaidasofia/claude-deconstruct\"></a>\n  <a href=\"https://myceliumai.co\"><img alt=\"Built by Mycelium AI\" src=\"https://img.shields.io/badge/built_by-Mycelium_AI-15B89A\"></a>\n</p>\n\n<!-- mycelium-badges:end -->\n\nA Claude Code plugin for first-principles analysis. Surfaces hidden assumptions, establishes foundational truths, rebuilds the problem from scratch, and identifies the high-leverage move that conventional analysis would miss.\n\nModeled on Aristotle's method: find the truths that cannot be derived from anything more basic, then reason upward from those alone.\n\n---\n\n## What it does\n\nYou run `/deconstruct` and describe a problem, decision, or situation. The skill walks four phases:\n\n1. **Surface the assumptions** — what's embedded in how you framed it (and which are load-bearing)\n2. **Establish first principles** — what's true independent of convention or prior strategy\n3. **Rebuild from the foundation** — three distinct approaches, optimized for speed, impact, simplicity\n4. **The high-leverage move** — the single action that's invisible under conventional analysis\n\nTwo modes:\n- **Fast** (Phase 1 + Phase 4) — for daily decisions, auto-triggers\n- **Full** (all four phases) — for pricing, business models, career decisions, strategy pivots\n\nThe fear flag is built in: when an assumption traces back to fear, the skill names it and points to journaling instead of strategy. Fear-origin assumptions are rarely intellectual problems.\n\n---\n\n## Install\n\nOpen Claude Code, paste:\n\n    /plugin marketplace add adelaidasofia/claude-deconstruct\n    /plugin install claude-deconstruct@claude-deconstruct\n\nThen in any Claude Code session:\n\n```\n/deconstruct\n```\n\nThe skill will prompt for the problem you want to deconstruct.\n\n<details>\n<summary>Legacy install</summary>\n\n```bash\nclaude plugin add github.com/adelaidasofia/claude-deconstruct\n```\n\n</details>\n\n---\n\n## Requirements\n\n- Claude Code\n- Nothing else\n\n**Optional integrations:**\n- Decision template with `stakes: high` field — auto-offers fast mode on high-stakes entries (set `deconstruct_auto: true` in the decision frontmatter to enable)\n- The daily-journal or insights plugin — adds a \"first-principles audit\" step to weekly review (flags high-stakes decisions made without a deconstruct pass)\n\n---\n\n## When to run it\n\nThis skill works best when you suspect you're stuck inside assumptions you can't see:\n\n- A pricing model copied from competitors without questioning why\n- A product roadmap built on what users say they want vs. what they actually need\n- A career path followed because \"that's how it's done in this industry\"\n- A business model that feels stuck but can't figure out why\n- A hiring process, marketing strategy, or workflow everyone told you was \"best practice\"\n- A competitive analysis where you're parroting positioning instead of finding your edge\n- Any decision where \"we've always done it this way\" is the real answer\n\nThe full run is heavy. Don't run it on trivial decisions. Fast mode exists for a reason.\n\n---\n\n## What makes this different from \"list pros and cons\"\n\nPro/con lists assume the framing is correct. Deconstruction questions the framing.\n\nMost decision tools take your problem statement as given and help you optimize within it. This skill assumes the problem statement itself is contaminated by convention, imitation, precedent, fear, and unexamined defaults — and forces you to strip those out before you reason about solutions.\n\nThe 3-question test in Phase 2 is the core. If a statement is only true because everyone else does it, it's not a first principle. It's a habit.\n\n---\n\n## Submitting to the Cowork marketplace\n\nOnce the repo is on GitHub, submit at: **[clau.de/plugin-directory-submission](https://clau.de/plugin-directory-submission)**\n\nFor the community marketplace:\n\n```bash\nclaude plugin marketplace add anthropics/claude-plugins-community\n```\n\n---\n\n\n## Telemetry\n\nThis plugin sends a single anonymous install signal to `myceliumai.co` the first time it loads in a Claude Code session on a given machine.\n\n**What is sent:**\n- Plugin name (e.g. `slack-mcp`)\n- Plugin version (e.g. `0.1.0`)\n\n**What is NOT sent:**\n- No user identifiers, names, emails, tokens, or API keys\n- No file paths, message content, or anything from your work\n- No IP address is stored after dedup processing\n\n**Why:** Helps the maintainer know which plugins people actually install, so attention goes to the ones that get used.\n\n**Opt out:** Set the environment variable `MYCELIUM_NO_PING=1` before launching Claude Code. The hook will skip the network call entirely. Already-pinged installs leave a sentinel at `~/.mycelium/onboarded-<plugin>` — delete it if you want to reset state.\n\n## License\n\nMIT\n",
  "bytes": 5463,
  "sha": "f3e4f91f8a4893b6ba8862ed147fdfcb9d0e9cdac72acf29c5d9e7013b4d9f0f",
  "repo_slug": "adelaidasofia/claude-deconstruct",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_adelaidasofia_claude_deconstruct_claude__1f1b2db9/readme"
}