Dokkabei97

Dokkabei Harness — Development skill for Claude Code

Development community

Claude Code plugin marketplace — 20 plugins bundling loop-engineering harnesses, multi-agent teams, and gated dev workflows (hooks · skills · agents · commands).

How to install Dokkabei Harness

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Dokkabei97/dokkabei-harness and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Dokkabei Harness does

Claude Code plugin marketplace — 20 plugins bundling loop-engineering harnesses, multi-agent teams, and gated dev workflows (hooks · skills · agents · commands).

Alternatives in Development

IPolloWork — Enterprise-grade, local-first Agent Workbench for people and agent teams 4.9k ★
How Claude Code Works — Deep dive into Claude Code internals — architecture, agent loop, context engineering, and more 1.9k ★
Claude Code Everything You Need To Know — Ultimate all-in-one guide to mastering Claude Code 1.3k ★

README

**English** · [한국어](README_KO.md)

dokkabei-harness

Claude Code plugin marketplace. It started as a collection of sub agents, but now it bundles agents, commands, skills, and hooks together into **23 plugins** under `plugins/`, installed and distributed via `.claude-plugin/marketplace.json`.

Installation

/plugin marketplace add 
/plugin install @dokkabei-harness

Example: `/plugin install base@dokkabei-harness`, `/plugin install search@dokkabei-harness`.

★ Featured: `observe` — the self-measuring harness

Most plugins do work. **`observe` watches the harness itself** — which skills and agents actually fire, *why*, and whether they complete — and turns that into concrete improvements.

Claude Code's native `/usage` shows **cost and tokens**. observe shows the layer above it — **which skills and agents fire, why, whether they complete, and which go stale or uncorrected** — the harness-health view that cost metrics can't give you.

Inspired by Nous Research's **Hermes Agent**: where Hermes grows by autonomously *creating* skills from experience, observe takes the **evaluation-first** path — it *measures and proposes*. It ports the **deterministic half** of Hermes's curator (usage lifecycle: stale / archive candidates; correction signals) and surfaces dead/stale assets, missed activations, and uncorrected skill runs — then drafts the fix. **You approve; it never edits a file silently.**

Use it in three steps:

# 1. Turn on tracing (opt-in — records prompt text locally, so it's off by default)
export OBSERVE_TRACE=1

# 2. Work normally — 6 hooks correlation-log prompt → skill → agent → result → session
#    into .claude/skill-trace.jsonl (joined by session_id / prompt_id)

# 3. Ask for the report: deterministic aggregation → LLM interpretation → proposals
/observe-report   # unused & stale/archive candidates · missed activations
                  # correction signals · description-tuning dra