Borrowing it
Nothing to install: this file belongs to nuudge/nudge. 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/nuudge/nudge/main/AGENTS.mdgit clone --depth 1 https://github.com/nuudge/nudgeWrote 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/nuudge/nudge/agents-md)<a href="https://agentmods.dev/instructions/nuudge/nudge/agents-md"><img src="https://agentmods.dev/badge/instructions/nuudge/nudge/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/nuudge/nudge/agents-md"><img src="https://agentmods.dev/badge/instructions/nuudge/nudge/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 | $0.00542 | $0.00542 |
| Opus 5.5 | $0.00217 | $0.00217 |
| Sonnet 5.5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
nudge 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 today.
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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Instructions for AI agents (and humans) working in this repo.
Think before coding
- State your assumptions. If a request has several readings, say which you picked, or ask.
- If a simpler approach exists, say so and push back.
- If something is unclear, stop and name what is confusing.
Simplicity
Write the least code that solves the problem.
- No features, options, or abstractions that weren't asked for. Three similar lines beat a premature helper.
- No error handling for cases that can't happen. Validate at boundaries (user input, network, parsed data) and trust internal code and the type system.
- No backwards-compat shims or dead code kept "just in case". Git history is the record.
- If 200 lines could be 50, rewrite it.
Surgical changes
- Touch only what the task needs. Every changed line should trace back to the request.
- Don't refactor, reformat, or "improve" adjacent code. Mention unrelated problems instead of fixing them.
- Remove imports, variables, and functions your change made unused. Leave pre-existing dead code unless asked.
Comments
Default to no comment. Well-named code says what it does.
- Write a comment only for a non-obvious why: a hidden constraint, a subtle invariant, a workaround, behavior that would surprise the next reader.
- Keep it to one or two lines. If it needs a paragraph, the code or the design probably needs fixing instead.
- Never restate the code, narrate history ("previously", "now"), or reference the task, issue, or caller that motivated it. That belongs in the commit message.
- Older code in this repo is commented more heavily than this. Don't copy that density.
Docs
- Write like a human expert. Cut hedging, filler, and prose that restates the code.
- Describe the current state of the system. Leave out how it was built, what was tried, and future work; link an issue instead.
Verify
Turn the task into a check you can run, then loop until it passes: a bug fix gets a test that reproduces it, a refactor keeps the tests green before and after.
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.
- today First seen · 48 lines · 542 tokens per session scan A dc2d8f618fda
nudge AGENTS.md is an instructions file published in the GitHub repository nuudge/nudge (5 stars, last pushed today), licensed MIT. It adds 542 tokens to every session, about $0.0022 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 2026-11-14.
nudge AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nudge AGENTS.mdnuudge/nudge | Instructions file | 5 | today | MIT | A | 542 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 281k | yesterday | MIT | A | 4,335 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |