reatcat/l123-harness

中文 | English

A battle-tested agent methodology packaged as a plugin for both Claude Code and DeepSeek Harness (dsh) — one codebase, two hosts. Aligned with the "everything is a plugin" design: the host is the kernel; this plugin only contributes capability components — context injection, gates, event recording, memory distillation — each individually understandable, all removable as a whole. Project knowledge does not live in the plugin: after installation the project accumulates its own.

The four principles

1. State outside the model — conclusions, plans and progress go to disk; the context window only holds what the current task needs.
2. Objective observation — test red/green, command output and log data are evidence; reasoning is not.
3. No divergence in the inner loop — the spec governs the plan, the plan governs step boundaries, TDD governs stop conditions.
4. Upgrades require approval — memory is written freely; promotion to knowledge / skill / L1 / L2 requires explicit user approval.

Three-tier memory

Tier	Carrier	Character
L1 always-on	CLAUDE.md	Small, stable cache prefix: principles, priorities, safety floor, routing table
L2 index	.agents/INDEX.md	symptom → one-line rule → L3 pointer; injected automatically by the SessionStart hook
L3 detail	.agents/**	knowledge / pitfalls / runbooks / current / events / inbox

Install

Claude Code

# A: local development
claude --plugin-dir /path/to/l123-harness

# B: permanent personal install
cp -r l123-harness ~/.claude/skills/

# C: git distribution (this directory is a single-plugin marketplace)
#   /plugin marketplace add <git-repo>
#   /plugin install l123-harness

DeepSeek Harness (dsh)

The repository is also a standard dsh bundle (package.json declares dsh.bundle + a root cordis.patch.yml). Plain JavaScript, no build step — git installs need no pnpm build approval:

dsh plugin --profile web add github:reatcat/l123-harness

Local development note: dsh plugin add <local-path> uses a pnpm link:, which does not install this plugin's bridge dependency — hooks degrade (skills only, with a startup warning). To test locally, use a tarball: npm pack && dsh plugin --profile web add ./l123-harness-*.tgz, or run pnpm install inside the plugin directory first.

On mount, two things happen automatically:

1. Skills — the four methodology skills are registered on ctx.skills and surface through the standard skill tool;
2. Hooks bridge — the official @deepseek-ai/dsh-hooks-claude-code bridge is mounted and runs hooks/hooks.json as-is.

hooks.json event	dsh bridge	Notes
SessionStart (L2 injection + event)	✅	JSON additionalContext output, dual-host compatible
PreToolUse (gate-guard)	✅	matcher includes DSH edit/write/str_replace_editor; exit 2 → deny
PostToolUse (tool_error log)	✅	observation-only
Stop (boundary event)	✅	observation-only
PreCompact (checkpoint rescue)	⚠️ not bridged yet	config is safely ignored
SessionEnd (boundary event)	⚠️ not bridged yet	same as above

Usage

/l123-harness:init-harness     # bootstrap a project: L1/L2/L3 skeleton + gate list
/daily work: L2 index injected automatically; the gate blocks protected
/files; events are recorded automatically
/l123-harness:event-review     # weekly review: events → inbox candidates → triage

Under dsh the same skills are available as init-harness, event-review, tdd and write-a-skill through the skill tool and user commands.

Discipline quick reference

• Changing a protected file: explain to the user → approval → touch <project-root>/.claude/.gate-token → retry.
• .agents/inbox/ must not be read while working; candidates are not conclusions.
• .agents/events/ is read-only and immutable.
• Knowledge promotion path: context → memory (freely) → inbox (weekly review) → knowledge / L2 (human-approved).

License

MIT