claude

first-principles

A Claude Code plugin: the 5-phase first-principles methodology plus 15 namespaced skills — 8 companion-technique skills (Five Whys, pre-mortem, trade-off analysis, fishbone, inversion, second-order thinking, estimate, theoretical-limit), 5 focused-phase skills (identify-essence, challenge-assumptions, ground-truths, reason-upward, validate), the first-principles-analysis launcher, and the persona reader-view companion. Use when reasoning from ground truths rather than analogy or convention.

2 on GitHubby Christopher Davidsonv9.21.0MITupdated 30 days agoreasoning
/

Plugin first-principles from marketplace first-principles-skill in chrisdavidson/first-principles-skill. Commands read from the repo's manifest — 30 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (15)

  • challenge-assumptions

    Slash-only Phase 2 stub — classify and test every assumption before reasoning.

  • estimate

    Runs a focused estimate only — magnitude rebuild from units. Invoke via /estimate only.

  • first-principles-analysis

    Runs the full five-phase first-principles analysis. Slash-only.

  • fishbone

    Runs a focused fishbone only — breadth-first cause-category map. Invoke via /fishbone only.

  • five-whys

    Runs a focused 5-Whys only — root-cause drill on a symptom or a reduce-to-primitives irreducibility drill on a claim. Invoke via /five-whys only.

  • ground-truths

    Slash-only Phase 3 stub — compile GT-ID-anchored verified facts for derivation chains.

  • identify-essence

    Slash-only Phase 1 stub — expose core question by stripping framing artifacts.

  • inversion

    Runs a focused inversion only — enumerates failure preconditions. Invoke via /inversion only.

  • persona

    Writes a role-specific reader view of a delivered first-principles analysis to a sibling file, using only what the analysis already states; slash-only, never run automatically.

  • pre-mortem

    Runs a focused pre-mortem only — prospective-hindsight failure analysis. Invoke via /pre-mortem only.

  • reason-upward

    Slash-only Phase 4 stub — build derivation chains upward from named ground truths.

  • second-order

    Runs a focused second-order only — 2nd/3rd-order effects. Invoke via /second-order only.

  • theoretical-limit

    Strips conventions to the law-permitted ceiling. Invoke via /theoretical-limit only.

  • trade-off

    Runs a focused trade-off only — weighted-criteria scoring. Invoke via /trade-off only.

  • validate

    Slash-only Phase 5 stub — stress-test each derivation chain for weak links.

Subagents (1)

  • first-principles

    Runs a complete first-principles analysis end-to-end: decomposes the problem into verified ground truths, challenges every assumption, and reasons upward to a validated conclusion. Applies all eight companion techniques (5-Whys, fishbone, inversion, pre-mortem, trade-off, second-order thinking, esti

Hooks (1)

  • SubagentStop

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/delivery-guard.py"

View source on GitHub

Similar plugins

Appends two or three short follow-up questions after a substantive answer to help users check key facts, probe the reasoning, and notice missing context

19 skills

anthropics/skills 193,780

ruflo-sparc

claudecodex

SPARC methodology — Specification, Pseudocode, Architecture, Refinement, Completion phases with quality gates

3 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Test-driven development methodology with red-green-refactor cycles and code review

4 commands · 2 agents

wshobson/agents 42,461

Adversarial thinking partner for founders and executives. Stress-tests plans, prepares for board meetings, navigates hard calls, runs postmortems. 5 sub-skills with slash commands.

6 skills · 1 agent

alirezarezvani/claude-skills 29,725

Skills for building apps with the AG-UI .NET SDK: streaming chat (stateless vs hosted agents), server tools, client tools, human-in-the-loop (approvals & interrupts), shared state, multimodal messages, reasoning traces, protobuf transport, and troubleshooting.

9 skills

ag-ui-protocol/ag-ui 17,158

Maintain first-principles?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted