Habitat-Thinking

Habitat-Thinking/ai-literacy-superpowers

Cursor rule Cursor

Architectural constraints synced from HARNESS.md.

Habitat-Thinking/ai-literacy-superpowers

Cursor rule Cursor

Project conventions synced from HARNESS.md.

Habitat-Thinking/ai-literacy-superpowers

Plugin Claude Code

Bundles 41 skills, 17 commands, 20 agents, 3 hooks · 5,151 tokens together

The AI Literacy framework's complete development workflow — harness engineering, agent orchestration, literate programming, CUPID code review, compound learning, and the three enforcement loops.

Habitat-Thinking/ai-literacy-superpowers

Command GitHub Copilot

Run an AI literacy assessment — scan the repo for evidence, score three disciplines, produce a timestamped report.

Habitat-Thinking/ai-literacy-superpowers

Command GitHub Copilot

Run the Choice Cartographer (decision-archaeology agent) on a spec — produces the choice-story record at docs/superpowers/stories/ .md; use after spec-mode /diaboli dispositions are resolved, before plan approval.

Habitat-Thinking/ai-literacy-superpowers

Command GitHub Copilot

Run the adversarial reviewer on a spec or implementation — produces the objection record at docs/superpowers/objections/ .md (spec mode) or -code.md (code mode); use after spec-writer completes or after the final code-reviewer PASS.

Habitat-Thinking/ai-literacy-superpowers

Command GitHub Copilot

Run a guided convention extraction session — surfaces tacit team knowledge through structured questions.

Habitat-Thinking/ai-literacy-superpowers

Command GitHub Copilot

Run a full meta-verification of the harness — check whether HARNESS.md matches reality.

Habitat-Thinking/ai-literacy-superpowers

Command GitHub Copilot

Add or promote a constraint in HARNESS.md.

Habitat-Thinking/ai-literacy-superpowers

Command GitHub Copilot

Run garbage collection checks against the codebase.

Habitat-Thinking/ai-literacy-superpowers

Command GitHub Copilot

Generate a harness health snapshot with enforcement status, trends, and meta-observability checks.

Habitat-Thinking/ai-literacy-superpowers

Command GitHub Copilot

Initialize a harness for the current project — discover stack, ask about conventions, generate HARNESS.md.

Habitat-Thinking/ai-literacy-superpowers

Command GitHub Copilot

Show current harness health — enforcement ratio, drift, and garbage collection state.

Habitat-Thinking/ai-literacy-superpowers

Command GitHub Copilot

Capture a reflection after completing work — what was surprising, what should future agents know, what could improve.

Habitat-Thinking/ai-literacy-superpowers

Command GitHub Copilot

Watch the human verifier the harness cannot verify — Read mode dispatches the reservoir-warden agent for a fuller cognitive-reservoir read; Tune mode helps you edit the HARNESS.md Cognitive reservoir block (thresholds and chronotype), proposing edits for you to confirm.

Habitat-Thinking/ai-literacy-superpowers

Command GitHub Copilot

Full habitat setup — generates CLAUDE.md, HARNESS.md, AGENTS.md, MODELROUTING.md, REFLECTIONLOG.md, agents, CI templates.

Habitat-Thinking/ai-literacy-superpowers

Command GitHub Copilot

Show the full habitat status — harness health, agent team, compound learning, model routing, CI coverage.

Habitat-Thinking/ai-literacy-superpowers

Command GitHub Copilot

Manage git worktrees for parallel agent isolation — spin up, merge back, or clean up.

Habitat-Thinking/ai-literacy-superpowers

Plugin Claude Code

Bundles 2 commands, 1 agent · 704 tokens together

Agents accountable for helping to maintain human understanding. The first agent builds, self-challenges, and cross-checks two models of a codebase scope — architectural moving parts and domain concepts — and surfaces the mutually-corrected models on demand. Future agents will extend the discipline to other domains.

Habitat-Thinking/ai-literacy-superpowers

Plugin Claude Code

Bundles 1 skill, 1 command, 1 agent · 205 tokens together

Researches and authors Mitchell-extended model cards from a model name. Tiered source strategy (provider docs → HuggingFace → arXiv → web). Hybrid review-before-commit flow.