Borrowing it
Nothing to install: this file belongs to SeoNaRu/nulnul-harness. 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/SeoNaRu/nulnul-harness/main/AGENTS.mdgit clone --depth 1 https://github.com/SeoNaRu/nulnul-harnessWrote 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/seonaru/nulnul-harness/agents-md)<a href="https://agentmods.dev/instructions/seonaru/nulnul-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/seonaru/nulnul-harness/agents-md/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/instructions/seonaru/nulnul-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/seonaru/nulnul-harness/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00953 | $0.00953 |
| Opus 5.5 | $0.00381 | $0.00381 |
| Sonnet 5.5 | $0.00191 | $0.00191 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
nulnul-harness 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 1mo 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nulnul harness working agreement
This repository builds plugins/nulnul-harness/, a Codex plugin that selects the strongest justified project-local capability system for the requested outcome, verifies the user's work, removes non-contributing setup, and evolves from measured outcomes without requiring users to operate a harness. Simplicity breaks ties between materially equivalent outcome paths; agent, skill, plugin, context, and infrastructure counts are never primary goals.
- Treat
plugins/nulnul-harness/as the only shipped product boundary. - Keep the plugin skills-only until a real workflow proves that an MCP server, hook, app, or external service is necessary.
- Inspect a target repository before asking questions. Ask only for product decisions or constraints that cannot be discovered safely. A request to set the harness up on a repository that already has work is never one of those questions.
- Continue the user's original task after setup; setup alone is not task completion.
- Select the non-overlapping capability set expected to produce the strongest verified task outcome. Among materially equivalent paths, choose the one with lower context, coordination, runtime, maintenance, and permission cost; activate only what the current task needs.
- Use direct or single-agent execution when it is outcome-competitive. Add as many bounded roles as materially improve specialization, context isolation, parallel work, or independent verification; agent count has no target and one owner keeps final synthesis.
- Never register global tools, use credentials, deploy, or publish without explicit user approval.
- Give every state file one writing process, keep
unknowndistinct fromverifiedandfailed, persist cursors on empty cycles, and prove each validity check against a negative control. - Update the harness documents, exact evidence counts, and locale-parity claims in the same change as the code or release evidence they describe.
Read only when the work needs it
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.
- 1mo ago Changed · -3 lines · -1,049 tokens per session b7f95128a0db
- 1mo ago Changed · +2 lines · +115 tokens per session df209f5c7dc2
- 1mo ago Changed · +2 lines · +180 tokens per session 659325bc726f
- 1mo ago Changed · +1 lines · +152 tokens per session 77e6ac1f41b4
- 1mo ago First seen · 47 lines · 1,555 tokens per session scan A 0dc1d06abb46
nulnul-harness AGENTS.md is an instructions file published in the GitHub repository SeoNaRu/nulnul-harness (34 stars, last pushed 1mo ago), licensed MIT. It adds 953 tokens to every session, about $0.0038 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.