aaronbassett

aaronbassett/agent-foundry

Plugin Claude Code

Plugin marketplace listing 21 plugins: constitution, dev-specialisms, devs, flutter-core, git-lovely.

aaronbassett/agent-foundry

Plugin Claude Code

Create, validate, and enforce project constitutions with living governance.

aaronbassett/agent-foundry

Agent

Review code against project constitution with severity-rated violation reports. Use when user asks to 'review for compliance', 'check constitution violations', 'validate changes against principles', or when stop hook blocks due to unvalidated changes. Supports full project, staged changes, git diff, and GitHub PR…

aaronbassett/agent-foundry

Skill Claude CodeCodex

Amend project constitution with semantic versioning and changelog management. Use when user asks to "amend constitution", "update constitution version", "add principle", or "modify governance rules". Automatically regenerates checklist.

aaronbassett/agent-foundry

Skill Claude CodeCodex

Distill CONSTITUTION.md into 6-12 actionable checklist items with semantic deduplication. Use when user asks to "generate checklist", "create action items from constitution", or after amendments to regenerate verification tasks.

aaronbassett/agent-foundry

Skill Claude CodeCodex

Add a tailored constitution to your project. Use when starting a new project, bootstrapping governance, or when user asks to "create a constitution", "set up project principles", or "define coding standards". Conducts structured discovery through clarifying questions about project scale, risk profile, lifespan…

aaronbassett/agent-foundry

Plugin Claude Code

Seven structured decision-making techniques (tribunal, adversarial, red-team, pre-mortem, council, ladder-of-abstraction, calibration) that exploit the subagent architecture to produce verdicts plan steps can branch on. Includes a routing skill and two custom subagent types (Advocate, Lens).

aaronbassett/agent-foundry

Agent

Use only when dispatched by the /decision-making:tribunal command. Argues vigorously for an assigned option across multiple deliberation rounds, rebuts opposing arguments, acknowledges genuine weaknesses in good faith, and commits fully to the assigned position. Not for user-facing invocation.

aaronbassett/agent-foundry

Agent

Use only when dispatched by the /decision-making:council command. Inhabits a specific assigned perspective (e.g., ops engineer, new hire, security reviewer) and writes a position statement from that perspective alone. Does not see other lenses' outputs. Does not meta-comment on the deliberation. Not for user-facing…

aaronbassett/agent-foundry

Command

Lightweight one-shot adversarial deliberation. Spawns steelmanned advocates for each option in parallel, then renders a verdict. Use for quick tiebreaks on reversible decisions.

aaronbassett/agent-foundry

Command

Spawns 3 independent estimators for quantitative or probabilistic questions, compares their estimates, and derives confidence from the spread. Fan-out is fixed at 3.

aaronbassett/agent-foundry

Command

Spawns 4-6 lens subagents, each inhabiting a distinct perspective, then synthesizes their positions. Use for ambiguous, value-laden, or multi-stakeholder questions where framing matters.

aaronbassett/agent-foundry

Command

Reframes a question at progressively higher and lower altitudes via two parallel subagents (climber and descender). Use when the framing feels wrong or options feel forced.

aaronbassett/agent-foundry

Command

Imagines a tentative decision has failed catastrophically 6 months from now, then spawns subagents to write the post-mortems. Surfaces concrete failure modes before commitment.

aaronbassett/agent-foundry

Command

Stress-tests a proposed plan, answer, design, or artifact by spawning a committed adversarial subagent that finds the strongest reasons it will fail. Verdict is accept | revise | reject.

aaronbassett/agent-foundry

Command

Heavyweight adversarial deliberation with fact-finding, parallel advocates, rebuttals, judge questions, and up to 10 iteration rounds. Use for load-bearing, hard-to-reverse decisions.

aaronbassett/agent-foundry

Skill Claude CodeCodex

Plan steps that already know which command to invoke should call the command directly and skip this skill. Use this skill only when you need to pick a decision-making technique for the current question — it matches the decision shape against seven techniques (tribunal, adversarial, red-team, pre-mortem, council…

aaronbassett/agent-foundry

Plugin Claude Code

Create, implement, review, and visualize opinionated design systems that resist AI slop convergence.

aaronbassett/agent-foundry

Skill Claude CodeCodex

Create an opinionated design system as a DESIGN.md file. Triggers on: "create a design system", "generate DESIGN.md", "design system for [description]", "new design system", "design system", or /design-systems:create. Generates a complete DESIGN.md with Creative North Star, Core Prohibitions, Anti-Moodboard, and full…

aaronbassett/agent-foundry

Skill Claude CodeCodex

Apply a DESIGN.md design system to the project's existing CSS/style files. Triggers on: "implement the design system", "apply design system", "set up design tokens", "apply DESIGN.md", or /design-systems:implement. Reads DESIGN.md, detects the project's CSS framework, and updates style files with design tokens.

aaronbassett/agent-foundry

Skill Claude CodeCodex

Audit UI code for design system compliance and AI slop markers. Triggers on: "review design system", "check design compliance", "audit UI code", "design system review", "check for AI slop", "design review", or /design-systems:review. Scans CSS, SCSS, JSX, TSX, Vue, and Svelte files against DESIGN.md rules and the AI…

aaronbassett/agent-foundry

Skill Claude CodeCodex

Generate a self-contained HTML specimen page that renders the design system live. Triggers on: "generate specimen", "preview design system", "show design system", "specimen page", "visualize design system", or /design-systems:specimen. Produces a single HTML file with all tokens rendered as visual examples.

aaronbassett/agent-foundry

Plugin Claude Code

Niche developer skills.

aaronbassett/agent-foundry

Skill Claude CodeCodex

Quick MVP deployment to fly.io for JavaScript (Next.js, RedwoodSDK, Express), Rust (Axum, Rocket), Python (FastAPI), and generic Dockerfiles. Use when deploying applications to fly.io, setting up databases (Postgres, volumes, Tigris object storage), managing secrets, configuring custom domains, setting up GitHub…