kodflow-hooks

Language, platform and concern specialists that routing dispatches to. Each verifies an API, a default, a limit or a deprecation against documentation before asserting it, returns what it consulted and what it could not confirm, and tries to break its own finding before reporting it.

35 agents

Combat animation that is anatomically and martially right, for a game project that enables it in its own settings (never installed by install.sh). /move briefs a panel — anatomy, six martial areas with the declared tradition governing, animation craft, rig, Godot and three.js — and writes measurable constraints with their sources; /anim-review measures sampled clips against them and asks the owner's verdict; /anim-feedback keeps every verdict as an ADR that later runs read first; /reference fetches reference images with their licence; /meshy generates characters, weapons and props with Meshy, fetches them with their licence and judges them against the rig.

5 skills · 14 agents · hooks

The work loop: open a tracked piece of work, research it, plan it, argue the plan, turn it into an executable contract, ship it. Each skill hands the next exactly what it needs, and every step leaves a trail the next session can read.

12 skills

Evidence-bound review and debugging. Findings cite real code and a counterexample; deterministic scanners run for real and their exit codes populate the report; an external non-LLM verifier can invalidate the whole run. Root-cause-first debugging refuses a fix nobody proved.

7 skills

Infrastructure, environment health and template sync — Terraform and Terragrunt work, a health check for this configuration itself, and the update path back to the upstream template.

5 skills

The shell side of the harness: super-claude as a real command on PATH instead of an alias, a TAB session picker that only offers conversations that still exist — matched on the words of their title, coloured by age — and housekeeping that deletes a session with everything keyed to its id. A SessionStart hook re-syncs it from the plugin at every launch, so updating the marketplace updates the shell. The same hook installs the status-line binary from its releases when it is missing, so a marketplace update is all it takes to get it.

1 skill · hooks

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.

7 skills · 1 command · 3 agents

CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents

3 skills · 1 MCP server · hooks

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

Headroom startup hooks for Claude Code and GitHub Copilot CLI.

hooks

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks