Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/armanas/froglet/agents-mdgit clone --depth 1 https://github.com/armanas/frogletWhat 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 | $0.00885 | $0.00885 |
| Opus 5 | $0.00443 | $0.00443 |
| Sonnet 5 | $0.00177 | $0.00177 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
froglet 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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Scope
- These instructions apply to the entire repository unless a deeper
AGENTS.mdoverrides them.
Project Overview
- Core Froglet implementation is in Rust under
src/, with binary entrypoints insrc/bin/. - Rust integration and conformance tests live in
tests/. - Python client helpers, adapters, and unittests live in
python/. - The OpenClaw/NemoClaw plugin lives in
integrations/openclaw/froglet/. - Protocol and operator docs live in
docs/KERNEL.md,docs/, andconformance/.
Change Boundaries
- Treat
docs/KERNEL.mdas the authoritative kernel specification. Do not change canonical artifact payloads, hashing, signing bytes, state transitions, or Lightning settlement bindings without explicit interoperability justification and prior discussion. - If you touch signing, hashing, or artifact structure, update
conformance/kernel_v1.jsonand explain why in the change summary. - Keep kernel changes small. Prefer adapters, higher layers, or integrations unless a change truly belongs in the signed protocol/runtime core.
- Public code must not depend on ignored
private_work/incubations.
Working Style
- Prefer editing existing files over adding new ones.
- Keep changes scoped to the task; avoid broad refactors unless they are required.
- Match existing Rust, Python, and JavaScript patterns already used nearby.
- Do not commit generated artifacts, local databases, or scratch outputs from
target/,_tmp/,data/,node.db*,private_work/, coverage caches, or IDE folders.
Key Paths
src/: Rust library code for protocol, runtime, provider, storage, and execution.src/bin/: Executable entrypoint forfroglet-node.tests/: Rust integration tests such as runtime routes, payments/discovery, and kernel conformance vectors.python/: Python SDK-style helpers pluspython/tests/.integrations/shared/froglet-lib/: Shared HTTP client and utilities used by both OpenClaw plugin and MCP server.integrations/openclaw/froglet/: OpenClaw/NemoClaw JavaScript plugin, scripts, and Node-based tests.integrations/mcp/froglet/: MCP server for external agent hosts (Claude Code, Cursor, Windsurf, etc.).scripts/strict_checks.sh: Full validation matrix used before PRs.compose*.yaml: Local multi-service compose setups.
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.
- 2d ago First seen · 57 lines · 885 tokens per session scan A fd687e9c7215
froglet AGENTS.md is an instructions file published in the GitHub repository armanas/froglet (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 885 tokens to every session, about $0.0044 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
bitterbot-desktop AGENTS.md
Instructions for Bitterbot-AI/bitterbot-desktop, covering bitterbot — repository guidelines, what is bitterbot?, what makes bitterbot different, 1. memory system (src/memory/) and 2. dream engine (src/memory/dream-engine.ts).
polar copilot-instructions.md
Instructions for jamaljsr/polar, covering polar - ai coding assistant instructions, core architecture, network orchestration via docker compose, state management (easy-peasy + redux) and visual designer (react flow chart).
AgentNetworkProtocol AGENTS.md
Instructions for agent-network-protocol/AgentNetworkProtocol, covering repository guidelines, project structure & module organization, protocol ownership boundary, build, test, and development commands and coding style & naming conventions.
Cotal AGENTS.md
Instructions for Cotal-AI/Cotal, covering agents.md, what this is, read these first, commands and repository map.
protocol-launcher AGENTS.md
Instructions for zhensherlock/protocol-launcher, covering agents.md - protocol launcher, repo shape, commands that matter, protocol library and docs.
t2000 CLAUDE.md
Instructions for mission69b/t2000, covering claude.md, architecture — the big picture, what this monorepo is (product first), three brands / repos and this repo structure.