Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Rainnystone/naive-harness-kit --skill welcome-to-nhkgit clone --depth 1 https://github.com/Rainnystone/naive-harness-kitWrote 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/rainnystone/naive-harness-kit/welcome-to-nhk)<a href="https://agentmods.dev/skills/rainnystone/naive-harness-kit/welcome-to-nhk"><img src="https://agentmods.dev/badge/skills/rainnystone/naive-harness-kit/welcome-to-nhk/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rainnystone/naive-harness-kit/welcome-to-nhk"><img src="https://agentmods.dev/badge/skills/rainnystone/naive-harness-kit/welcome-to-nhk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.00951 |
| Opus 5 | $0.00013 | $0.00476 |
| Sonnet 5 | $0.00005 | $0.00190 |
| Haiku 4.5 | $0.00003 | $0.00095 |
Grade A, and why
welcome-to-nhk 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Welcome To NHK
Use this skill as the first-stop router. It selects nhk-bootstrap, nhk-upkeep, or nhk-archive; it does not perform those workflows itself.
1. Check Peer Dependencies
Treat superpowers and planning-with-files as peer dependencies.
- Check whether both are available before inspecting or changing NHK surfaces.
- If either is missing, stop and ask the user to install, enable, or explicitly adopt it.
- Adopt is permission to follow that dependency's conventions manually for this NHK run only. It creates no persistent marker and is not installation.
- Carry adopted-dependency status into any handoff. Whichever skill delivers the result must report that the dependency was not installed and its conventions were followed manually for this NHK run; if this router ends the flow, report it here.
- If the user does not choose a mode, do not continue. Never silently emulate a missing workflow.
- Use
../references/dependency-setup.mdwhen the user needs the sources or decision boundaries.
2. Identify The Canonical Instruction Source
A valid thin import is a line whose trimmed content is exactly @AGENTS.md or @./AGENTS.md, outside fenced code, Markdown blockquotes, and comments. Mentions in prose, examples, quoted text, code fences, or comments do not count.
Claude @ imports of any companion doc are not topology signals and are not valid NHK routing. Companion docs must be named by literal path and loaded only when the task requires them.
Apply this order:
- Only
AGENTS.mdexists: it is canonical. - Only an ordinary
CLAUDE.mdexists: it is the standalone canonical source. - Both exist and
CLAUDE.mdcontains a valid thin import:AGENTS.mdis canonical andCLAUDE.mdis its thin adapter. Do not ask which is active. - Only
CLAUDE.mdexists and it contains a valid thin import: this is a broken adapter. Ask whether to restoreAGENTS.mdor convertCLAUDE.mdto standalone. - Both exist without a valid thin import: this is real ambiguity. Ask which source should be canonical and do not modify either file.
- Neither exists: use environment and workspace signals only now. If they do not identify one format clearly, ask the user.
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.
- 2d ago Changed 6d09a9e713f7
- 5d ago Changed · +2 lines d7bc46964d70
- 12d ago First seen · 70 lines · 25 tokens per session scan A 618456abc749
welcome-to-nhk is a skill published in the GitHub repository Rainnystone/naive-harness-kit (21 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 951 once invoked, about $0.0001 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
daemon
Continuous autonomous operation mode. Keeps campaigns running 24/7 by chaining Claude Code sessions via RemoteTrigger. Each session picks up from the campaign's continuation state, works until context runs low or the phase completes, then schedules the next session. Auto-stops on campaign completion or budget…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
setup
First-run experience for the harness. Three modes: Recommended (guided, 3 min), Full Tour (guided + skill walkthrough, 8 min), and Express (zero questions, 30 sec). Installs hooks first, detects stack, configures harness.json, runs a live demo on real code, and prints a reference card.
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
ascii-diagram
Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.