context-engineering commands

AKSoftCode/aicrew

Command

Use when starting any development task — bug fix, feature, or refactor.

AKSoftCode/aicrew

Command

Scout → Act flow with graph-first discovery, speculative context, and Karpathy guardrails (no full /dev pipeline).

AKSoftCode/aicrew

Command

Use when maintaining, improving, or adding to the /Agents/ skills system.

TidyFactor/Cinematic

Command Codex

A read-only report against both checklists that govern this track — memory/09-quality-bar.md (cinematic auto-rejects) and memory/11-brand-json.md (token compliance). The original AGENTS.md only ran these checks inline at the end of a fresh build; this command makes them runnable on their own against an…

TidyFactor/Cinematic

Command Codex

Command "clone-brand" from TidyFactor/Cinematic, covering purpose, when to run it, what it does, output convention and checklist.

TidyFactor/Cinematic

Command Codex

Bring an existing static landing page, a different generator's output, or a client-supplied design onto the cinematic engine. This is the lifecycle mode the original AGENTS.md flow didn't cover — that flow only ever built fresh (init). Every other TidyFactor track ships Init/Convert/Improve; this command is what…

bluzername/claude-code-power-stack

Command

Generate a quick personal standup summary using all Power Stack tools. Run this at the start of your day to remember where you left off.

bluzername/claude-code-power-stack

Command

Generate a team standup summary using the shared team log and individual context.

bluzername/claude-code-power-stack

Command

Summarize what was accomplished in this session and offer to log key items for the team.

codeverbojan/claude-code-kickstart

Command Claude Code

New feature playbook — plan, build in phases, verify each phase.

codeverbojan/claude-code-kickstart

Command Claude Code

Analyze the codebase and auto-generate CLAUDE.md Section 10 project config.

codeverbojan/claude-code-kickstart

Command Claude Code

Analyze the codebase and extract real patterns into patterns.md.

emtcmca/promptsmith

Command

Author a complete, reusable agent system prompt from a short description — role, objective, method, guardrails, output contract, and baked-in push-back.

emtcmca/promptsmith

Command

Review a prompt, page, component, or draft through expert lenses (findings), fix it in place with --fix, or grade a prompt against a rubric with --grade (verdict + --against comparison).

emtcmca/promptsmith

Command

Coordinate multiple specialist agents on a multi-domain request — sharpen, decompose, dispatch the gallery, resolve seams, and synthesize one deliverable. (Layer 2 — requires a host that can spawn subagents.).

agenisea/turing

Command

Manually preserve session state and create ADRs for architecturally significant decisions using the TURING protocol.

agenisea/turing

Command

Display TURING memory status — sessions, tokens, and ADRs for current project or workstation.

Wolfe-Jam/bun-sticky-faf

Command Claude Code

Run bun-sticky on the current directory to check FAF score.

Wolfe-Jam/bun-sticky-faf

Command Claude Code

Run the championship-grade test suite and report results.

conorbronsdon/agent-memory-kit

Command

Walk a dream proposal artifact, review each item, apply accepted ones, commit.

conorbronsdon/agent-memory-kit

Command

Run a curator pass over the memory dir. Produces a proposal artifact for /dream-apply. Default curator: rot.

conorbronsdon/agent-memory-kit

Command

End a session — log what happened and propose durable memory updates.

hdk10/orgkit

Command

Model-driven lesson capture — read recent work in a role, distill genuine insights, append tagged bullets to pending.md. The real capture path; complements the Stop-hook's cheap regex fast-lane.

hdk10/orgkit

Command

Safely migrate existing folders into role directories — dry-run preview first, auto-fix literal path strings, then the model handles import statements and relative paths it flags. Never claims success silently.