ai-coding commands

2,407 tagged ai-coding, measured the same way as everything else here.

Browse within: agentic-coding 294agent-orchestration 140ai-assistant 122claude-ai 102spec-driven-development 98ai-workflow 97ai-development 84code-quality 83ai-security 79ai-governance 70ai-pair-programming 69ai-assisted-development 67ai-memory 67best-practices 64

memory

290

TheColliery/CoalTipple

Command

Part of coaltipple

Set up or change CoalTipple's memory anchor (on | off | set ) — the context a fresh worker reads.

not rated 6 4d ago A 26 tokens original Apache-2.0

off

291

TheColliery/CoalTipple

Command

Part of coaltipple

Turn CoalTipple routing OFF for this session — work as a normal single agent.

not rated 6 4d ago A 16 tokens original Apache-2.0

stats

292

TheColliery/CoalTipple

Command

Part of coaltipple

CoalTipple routing stats — approximate token savings and delegate-down / escalate-up activity this session.

not rated 6 4d ago A 18 tokens original Apache-2.0

my_brand

295

anilcancakir/claude-code-plugins

Command

Part of project-optimizer

Interactive brand identity creation with archetypes, colors, typography, and voice guidelines. Use when user mentions "brand", "colors", "typography", "brand.md", "design system", or "visual identity".

not rated 6 7mo ago A 46 tokens original MIT

audit-quick

296

telus-labs/stagecraft

Command

Run a quick codebase orientation scan — Phases 0 and 1 only (architecture map + health assessment). Skips deep analysis (security, performance, code quality) and the roadmap. Good for onboarding onto a new project or a fast pre-review checkup. Run /audit --resume later to continue with the deep phases.

not rated 6 6d ago A 67 tokens original MIT

audit

297

telus-labs/stagecraft

Command

Run a structured codebase audit. Maps the architecture, assesses health (compliance, tests, docs), performs deep analysis (security, performance, code quality), and synthesizes a prioritized roadmap. Outputs land under docs/audit/ in this project. Phases 0-3 with human checkpoints between each phase. Use /audit-quick…

not rated 6 6d ago A 78 tokens original MIT

devteam

298

telus-labs/stagecraft

Command

Run a stage of the Stagecraft pipeline. Wraps the devteam CLI so you can dispatch a stage (PM brief, design, build, review, QA, deploy, etc.) from inside Claude Code. The CLI emits the role-specific prompt; you invoke the matching subagent (under .claude/agents/) to do the work.

not rated 6 6d ago A 71 tokens original MIT

dejavu-pg-rescue

301

HthSolid/claude-dejavu

Command

Part of claude-dejavu

Postgres corruption rescue toolkit — scan, patch-toast, reset-flags, rebuild-table, reindex. Codifies the 2026-05-14 disk-full rescue playbook.

not rated 6 3mo ago A 37 tokens

restart

302

yacb2/claude-restart

Command

Restart Claude Code session (exit + auto-resume).

not rated 6 27d ago A 11 tokens original MIT

audit

303

davesheffer/hunch

Command Claude Code

Run an audit and record what it finds into Hunch as findings (observed gaps, no code change).

not rated 6 3d ago A 22 tokens original Apache-2.0

capture

304

davesheffer/hunch

Command Claude Code

Capture an engineering decision into Hunch's graph via a grilling interview (topic, rationale, rejected alternatives).

not rated 6 3d ago A 21 tokens original Apache-2.0

heal

305

davesheffer/hunch

Command Claude Code

Reconcile docs/code with Hunch's decision graph (doc≠graph drift), never rewriting prose silently.

not rated 6 3d ago A 21 tokens original Apache-2.0

debug

306

jzl-maker/EA-SKILL

Command

A command-line debugging toolkit for embedded programs using J-Link or OpenOCD, tools that connect a computer to a microcontroller for inspection.

not rated 6 +2 6d ago A 0 tokens original MIT

la

307

jzl-maker/EA-SKILL

Command

A command for capturing and decoding signals with a Saleae logic analyzer, a device that records electrical digital signals over time. It supports buses such as UART, SPI, and I2C, which are common ways chips communicate with peripherals.

not rated 6 +2 6d ago A 0 tokens original MIT

scope

308

jzl-maker/EA-SKILL

Command

A command for connecting to supported oscilloscopes, capturing or reading waveforms, measuring them, and saving results as CSV files or plots. An oscilloscope is a device that displays changing electrical signals.

not rated 6 +2 6d ago A 0 tokens original MIT

audit

309

Dragoon0x/canon

Command

Run a complete design audit of the current interface against CANON standards. Checks typography, color, spacing, motion, interaction, responsive behavior, accessibility, forms, depth, states, performance, and UX writing. Reports violations grouped by severity.

not rated 5 4mo ago A 50 tokens original MIT

normalize

310

Dragoon0x/canon

Command

Normalize the codebase to the CANON token system. Extract scattered values into design tokens for color, type, spacing, radius, shadow, z-index, motion. Replace ad-hoc values with references. Use when the codebase has drifted into magic numbers.

not rated 5 4mo ago A 55 tokens original MIT

teach

311

Dragoon0x/canon

Command

Explain a CANON rule or decision in plain language with before/after examples.

not rated 5 4mo ago A 18 tokens original MIT

assistant-auto

312

christopherlouet/claude-base

Command Claude Code

Orchestrator in automatic mode. Choose the workflow that semantically fits based on the request + the injected repo context, then execute immediately via Skill.

not rated 5 yesterday A 0 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: