Skip to content
Back to skills

Harness Principles

ASecurity

Auto-triggers on structural harness decisions: new chain primitive, new flow, remove evaluator, wrap evaluator, redesign harness, scaffolding, load-bearing, model upgrade, harness audit, refactor flow, sub-agent. Also triggers on file mentions of `src/application/chain/`, `src/application/flows/`, `src/integration/ai/providers/_engine/`. Instructs the agent to read the principles doc before proceeding.

  • 24 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 2, 2026
ai-agents

Security analysis

A100/100

Scanned September 2, 2026

npx -y skills add lukas-grigis/ralphctl --skill harness-principles --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Harness Principles?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Harness Principles
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/lukas-grigis-harness-principles/badge)](https://www.skillsdirectory.com/skills/lukas-grigis-harness-principles)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: harness-principles
description: 'Auto-triggers on structural harness decisions: new chain primitive, new flow, remove evaluator, wrap evaluator, redesign harness, scaffolding, load-bearing, model upgrade, harness audit, refactor flow, sub-agent. Also triggers on file mentions of `src/application/chain/`, `src/application/flows/`, `src/integration/ai/providers/_engine/`. Instructs the agent to read the principles doc before proceeding.'
when_to_use: 'When the user prompt contains any of: "chain primitive", "new flow", "remove evaluator", "wrap evaluator", "redesign harness", "scaffolding", "load-bearing", "model upgrade", "harness audit", "refactor flow", "sub-agent". Also when the prompt references `src/application/chain/`, `src/application/flows/`, or `src/integration/ai/providers/_engine/`. Not needed for pure business logic, UI, or persistence work that does not touch the chain or provider engine.'
---

# Harness Principles — Auto-trigger

This skill exists because the harness research evolves with model capability. What was load-bearing in
Opus 4.5 may be overhead in Opus 4.7. Without an explicit read-first gate, structural changes happen
without awareness of the research behind the current design.

**Before proceeding with any structural harness change:**

1. `Read .claude/docs/HARNESS-PRINCIPLES.md` in full.
2. Identify the relevant principle section(s) by name (e.g. "§ 14 Minimal scaffolding", "§ 7 Idle watchdog").
3. Note the current `ralphctl status` for each relevant principle (`applied` / `partial` / `gap`).
4. Proceed with the change, keeping the principle's intent visible in the diff.

If you are **removing** a harness component, confirm which principle the component implements and verify the
removal does not regress an `applied` row. If the removal moves a row from `applied` to `gap`, update
`HARNESS-PRINCIPLES.md` as part of the same commit.

If you are **adding** a new chain primitive — there are five and only five: `element` (interface), `leaf`,
`sequential`, `loop`, `guard`. Push back if a proposal adds a sixth. The principle behind this constraint
is § 14 (Minimal scaffolding) and the rationale is in `CLAUDE.md § Architecture invariants`.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.