Borrowing it
Nothing to install: this file belongs to smartfrog/opencode-froggy. 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/smartfrog/opencode-froggy/main/AGENTS.mdgit clone --depth 1 https://github.com/smartfrog/opencode-froggyWrote 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/smartfrog/opencode-froggy/agents-md)<a href="https://agentmods.dev/instructions/smartfrog/opencode-froggy/agents-md"><img src="https://agentmods.dev/badge/instructions/smartfrog/opencode-froggy/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/smartfrog/opencode-froggy/agents-md"><img src="https://agentmods.dev/badge/instructions/smartfrog/opencode-froggy/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 | $0.01122 | $0.01122 |
| Opus 5.5 | $0.00449 | $0.00449 |
| Sonnet 5.5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
opencode-froggy 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 7d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository is an OpenCode plugin written in TypeScript. The guidance below is for agentic coding tools that will modify or run code here.
Scope and structure
- Source code lives in
src/. - Tests live alongside sources in
src/**/*.test.ts. - Build output goes to
dist/. - Hooks configuration lives in
hook/hooks.md(YAML frontmatter). - Agents, commands, and skills are loaded from
agent/,command/, andskill/. - Skills are discovered by
skill/<name>/SKILL.md.
Setup
- Requires Bun 1.3+.
- Install dependencies with:
bun install
Build, typecheck, lint, test
There is no dedicated lint script or ESLint config. Use typecheck as the closest linting step.
- Build:
bun run build
- Typecheck (strict):
bun run typecheck
- Tests (all):
bun test
- Test coverage:
bun run test:coverage
- Test watch (local dev):
bun test --watch
Run a single test file
Bun is configured via bunfig.toml and runs src/**/*.test.ts.
Use any of the following:
bun test src/index.test.tsbun test src/index.test.ts --watch
Run a single test by name
bun test -t "should parse valid frontmatter"
Run a single test file and name
bun test src/index.test.ts -t "should parse valid frontmatter"
Optional quick checks
- Typecheck only:
bun run typecheck
- Build only:
bun run build
Code style and conventions
TypeScript
- Use TypeScript (ES module syntax) and keep
stricttype safety. - Avoid
any. Prefer explicit types or narrow types with guards. - Prefer
unknownfor untrusted data, then validate or narrow. - Prefer
Record<string, unknown>over loose object types. - Use
type-only imports for types (import { type Foo } ...).
Imports
- Use ESM imports, with
node:specifiers for core modules (Bun implements them):import { join } from "node:path"
- Prefer named imports; avoid default imports when not required.
- Keep imports grouped and ordered:
- Node core modules
- External dependencies
- Local modules
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.
- 7d ago Changed · +1 lines · -3 tokens per session 92b0165e1932
- 1mo ago First seen · 150 lines · 1,125 tokens per session scan A 1dda12be245d
opencode-froggy AGENTS.md is an instructions file published in the GitHub repository smartfrog/opencode-froggy (109 stars, last pushed yesterday), licensed MIT. It adds 1,122 tokens to every session, about $0.0045 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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.