Borrowing it
Nothing to install: this file belongs to Roots-and-Fruit/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/Roots-and-Fruit/skills/master/AGENTS.mdgit clone --depth 1 https://github.com/Roots-and-Fruit/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/roots-and-fruit/skills/agents-md)<a href="https://agentmods.dev/instructions/roots-and-fruit/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/roots-and-fruit/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/roots-and-fruit/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/roots-and-fruit/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 | $0.00447 | $0.00447 |
| Opus 5.5 | $0.00179 | $0.00179 |
| Sonnet 5.5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
skills 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 2mo 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.
What it actually says
Agent instructions — Roots & Fruit skills repo
Public-facing workflow packages for marketing and product agents. Read this file before editing any skill, fixture, or example in this repository.
Scope and audience
- Skills are domain-agnostic and client-agnostic. They must work for any user who installs them.
- Do not embed real client names, project codenames, internal URLs, or engagement-specific context in tracked files.
- Session context from a live client audit must not leak into skill edits, fixtures, or examples.
Examples and fixtures
- Use
example.comor other clearly fictional domains inSKILL.md,EXAMPLES.md, fixtures, and scorecards. - Real domains belong in user prompts only, not in committed artifacts.
- Fixture filenames and content stay generic (e.g.
example-saas,example-cloudflare-managed-origin-append).
Skill structure
| Path | Role |
|---|---|
marketing/skills/{skill}/SKILL.md |
Primary agent workflow (installable skill entry) |
marketing/skills/{skill}/REFERENCE.md |
Handoff schema, rubrics, templates |
marketing/skills/{skill}/REQUIREMENTS.md |
Data prerequisites |
marketing/skills/{skill}/EXAMPLES.md |
Sample prompts and output shapes |
marketing/skills/{skill}/scripts/ |
SSOT parsers and verifiers |
marketing/skills/{skill}/AGENTS.md |
Skill-specific maintainer notes (optional pointer here) |
Companion modules (e.g. CLOUDFLARE-MANAGED.md) live in the same skill folder and are invoked by the parent SKILL.md — they are not separate installable skills.
Verification before merge
Each skill documents its regression commands in SKILL.md. Run them after substantive changes. Do not claim completion without command output or explicit manual verification steps.
Secrets
Never commit API keys, .env values, or customer credentials. Use placeholders in docs and ${VAR} in MCP examples.
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.
- 2mo ago First seen · 47 lines · 447 tokens per session scan A bbb08bf4dfc0
skills AGENTS.md is an instructions file published in the GitHub repository Roots-and-Fruit/skills (11 stars, last pushed 2mo ago), licensed MIT. It adds 447 tokens to every session, about $0.0018 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.
skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skills AGENTS.mdRoots-and-Fruit/skills | Instructions file | 11 | 2mo ago | MIT | A | 447 | 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 | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |