Borrowing it
Nothing to install: this file belongs to PaulRBerg/agent-skills. 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/PaulRBerg/agent-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/PaulRBerg/agent-skillsWrote 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/paulrberg/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/paulrberg/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/paulrberg/agent-skills/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/paulrberg/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/paulrberg/agent-skills/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 | $0.03678 | $0.03678 |
| Opus 5.5 | $0.01471 | $0.01471 |
| Sonnet 5.5 | $0.00736 | $0.00736 |
| Haiku 4.5 | $0.00368 | $0.00368 |
Grade B, and why
agent-skills AGENTS.md scanned grade B with 1 finding 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 15d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `mcp/` contains MCP server launchers that `~/.claude.json` and `~/.codex/config.toml` run from this checkout. Edits How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Skills
This repository contains self-contained agent skills for Claude Code, Codex, and compatible agents. Keep README.md
minimal and human-facing. Put maintainer and agent guidance here.
Prompting Guidance
Write every skill and other agent-facing content for current Claude and GPT agent models, not for one model. Do not name
a model, a model version, or a model-specific default in that prose. Content that selects, configures, or attributes a
model is the exception, for example routing tables, model: frontmatter, and API parameters.
Base the guidance on the official vendor guides. Read both guides before complex, long-running, multi-tool, or orchestration-heavy work. Their recommendations may change.
- Anthropic prompting best practices: Covers all current Claude models. Its model-specific guidance table links each per-model prompting page.
- OpenAI latest-model guide: Covers the current GPT model family. Its prompting recommendations come from tests on one model in that family.
Treat advice that names a model as measured on that model. Apply it to other models only when the cross-model guidance supports it. When the guides give opposite corrections for different models, state the wanted behavior directly. Do not write a correction to one model's default, such as "be brief" or "write more".
The summaries below remind you of guidance that holds across current models. They do not replace the guides.
- State that user instructions take precedence over skills.
- Complete authorized work under stated assumptions. Name the premature stops to avoid and the stops that are wanted. Treat text-only turns as reports, not completion.
- Explore relevant sources before acting.
- Specify writing style, progress updates, and delegation preferences. Do not rely on model defaults for them.
- Name concrete patterns to avoid instead of giving generic style advice.
- Keep verification proportional to the change.
- Calibrate effort instead of prompting for more thinking. Never ask for reasoning in response text.
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.
- 15d ago Changed · +4 lines · +119 tokens per session e166ab90a69d
- 22d ago Changed · +13 lines · +285 tokens per session ac4037aad0a7
- 24d ago Changed · +2 lines · +56 tokens per session 17bf38acee47
- 25d ago Changed · +13 lines · +154 tokens per session c0d43ace2045
- 26d ago Changed · +3 lines · +69 tokens per session scan A → B f8dd88b8708a
- 1mo ago Changed · +39 lines · +567 tokens per session c3bd7d601f0d
- 1mo ago Changed · +5 lines · +113 tokens per session 80e18082db8e
- 1mo ago Changed · +2 lines · +46 tokens per session ed7de4ebbf2b
- 1mo ago Changed · +2 tokens per session 68953d3ecc1f
- 1mo ago First seen · 133 lines · 2,267 tokens per session scan A f5b2879fd3e5
agent-skills AGENTS.md is an instructions file published in the GitHub repository PaulRBerg/agent-skills (104 stars, last pushed yesterday), licensed MIT. It adds 3,678 tokens to every session, about $0.0147 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
agent-skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-skills AGENTS.mdPaulRBerg/agent-skills | Instructions file | 104 | yesterday | MIT | B | 3,678 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |