Borrowing it
Nothing to install: this file belongs to lukas-grigis/ralphctl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lukas-grigis/ralphctl/main/.claude/skills/harness-principles/SKILL.mdgit clone --depth 1 https://github.com/lukas-grigis/ralphctlWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lukas-grigis/ralphctl/harness-principles)<a href="https://agentmods.dev/skills/lukas-grigis/ralphctl/harness-principles"><img src="https://agentmods.dev/badge/skills/lukas-grigis/ralphctl/harness-principles.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00093 | $0.00525 |
| Opus 5 | $0.00046 | $0.00262 |
| Sonnet 5 | $0.00019 | $0.00105 |
| Haiku 4.5 | $0.00009 | $0.00052 |
Grade A, and why
harness-principles scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
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:
Read .claude/docs/HARNESS-PRINCIPLES.mdin full.- Identify the relevant principle section(s) by name (e.g. "§ 14 Minimal scaffolding", "§ 7 Idle watchdog").
- Note the current
ralphctl statusfor each relevant principle (applied/partial/gap). - 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.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 27 lines · 93 tokens per session scan A af609907b546
harness-principles is a skill published in the GitHub repository lukas-grigis/ralphctl (23 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 525 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
My Skill
Content here.
atomic-visual-options
Planning-phase visual comparison aid. Renders 2-4 side-by-side variants per decision dimension as a single throwaway, self-contained HTML file and captures the user's pick as typed terminal codes (e.g. "A2 B3"). Auto-fires on phrases like "show me a few options", "mock up some variants", "let me see this side by…
atomic-wiki
Conversational wiki and capture-bucket routing. Fires when the user wants a place, space, or folder for notes, research, tickets, raw dumps, or knowledge capture — checks the block in /.claude/CLAUDE.md; if the cwd is under a registered realm, creates the folder as a bucket via atomic wiki bucket add rather than a…
atomic-review
Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.
atomic-verify
Evidence-before-claim gate. Auto-triggers when Claude is about to claim "done", "fixed", "passing", "complete", "ready to merge", "looks good", "should work", "should pass", "green", or any synonym. Iron rule: no completion claim without a fresh verification command run in this turn. Explicit invocation…