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 agentmods add instructions/rainnystone/naive-harness-kit/agents-mdgit 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/instructions/rainnystone/naive-harness-kit/agents-md)<a href="https://agentmods.dev/instructions/rainnystone/naive-harness-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/rainnystone/naive-harness-kit/agents-md.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 | $0.00850 | $0.00850 |
| Opus 5 | $0.00425 | $0.00425 |
| Sonnet 5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
naive-harness-kit AGENTS.md 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 5d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NHK Repository Agent Instructions
This file is for coding agents working on the nhk repository itself.
It is not the end-user manual for NHK. Human-facing usage belongs in README.md and README_CN.md. Skill behavior belongs in the four skill folders. Frozen drafting assets belong in references/.
Repo Scope
Treat this repository as the clean publishable NHK package:
- repo-facing docs for humans
- agent-facing maintenance instructions
- four NHK skills
- frozen local references used by those skills
- maintainer-only deterministic validation in
scripts/andtests/
Do not turn this repository into a scratchpad for local planning artifacts from outside the package.
Documentation Roles
README.md: default GitHub landing page, English-first, written for humansREADME_CN.md: Chinese companion, written for humans, must stay aligned withREADME.mdAGENTS.md: shared repository instructions for Codex-style agentsCLAUDE.md: Claude Code entrypoint, should remain thin and import this filewelcome-to-nhk/,nhk-bootstrap/,nhk-upkeep/,nhk-archive/: actual skill behaviorreferences/: frozen reference assets, not casual dumping groundsscripts/: optional, read-only maintainer validation; not runtime skill contenttests/: maintainer tests for deterministic validation; not runtime skill content
Do not mix these roles. If a change is meant to teach humans how to use NHK, put it in the READMEs. If a change is meant to guide an agent maintaining this repository, put it here or in CLAUDE.md.
Editing Rules
- Keep NHK prompt-first, not hook-first.
- Preserve the current four-skill split unless there is a clear design reason to change it.
- Treat
references/as controlled assets. Update them deliberately, not casually. - If a reference or template explicitly says a subsection is verbatim-preserved, do not rewrite that subsection unless the human explicitly approves it.
- Do not silently remove the English/中文 cross-links between the two READMEs.
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.
- 5d ago First seen · 86 lines · 850 tokens per session scan A 698a43ac4e56
naive-harness-kit AGENTS.md is an instructions file published in the GitHub repository Rainnystone/naive-harness-kit (21 stars, last pushed 1mo ago), licensed MIT. It adds 850 tokens to every session, about $0.0042 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 instructions, from other repositories
moira AGENTS.md
AGENTS.md instructions for moira-mcp/moira, covering agents.md, what moira is, repository layout, build & run (fresh clone) and image: line and uncomment the build: block, then.
moira CLAUDE.md
Claude Code instructions for moira-mcp/moira, a project described as: Agent Workflow Engine for AI agents over MCP — per-step directives, completion conditions, and JSON-Schema validation. Self-hostable (Apache-2.0).
awaithumans-human-in-the-loop-ai-agents CLAUDE.md
Claude Code instructions for awaithumans/awaithumans-human-in-the-loop-ai-agents, covering awaithumans — codebase guide, what this project is, architecture overview, monorepo structure and package dependency rules.
Mira AGENTS.md
Instructions for byteseek/Mira, covering mira agent guide, read order, fast paths, research rules and expected artifacts.
cool-workflow AGENTS.md
AGENTS.md instructions for coo1white/cool-workflow, covering cool workflow — autonomous development agent, quick index, role, hard rule — never push directly to main and iteration loop.
pm-copilot AGENTS.md
AGENTS.md instructions for Leo-maomao/pm-copilot, covering pm copilot repository guidance, runtime loading, boundaries and verification.