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/0smallcat0/otto/agents-mdgit clone --depth 1 https://github.com/0Smallcat0/ottoWhat 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 | $0.01366 | $0.01366 |
| Opus 5 | $0.00683 | $0.00683 |
| Sonnet 5 | $0.00273 | $0.00273 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
otto 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 yesterday.
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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Product name: Otto (renamed 2026-07-08 from "Fincept Local Terminal"). The vision is an effortless, AI-operated local finance terminal — the user just gives commands. The "Fincept" references below are the clean-room heritage and boundary (the original product that was observed, never copied); they are intentionally kept, not the product name.
Purpose
This repository is a clean-room local rebuild of Fincept Terminal for local self-use. The governing product goal is functional and workflow parity with the observed Fincept Terminal experience while avoiding Fincept branding, assets, commercial copy, runtime binaries, and implementation-source copying. The source of truth is the research evidence under docs/reference/, direct observation of the installed app's behavior, and this file; it is not another project roadmap.
Non-Negotiable Boundary
- Do not implement or reference
D:\Crypto-Tradinggoals unless the user explicitly asks. - Do not treat
FINCEPT_TO_CRYPTO_TRADING_HANDOFF.mdas this repo's roadmap. - Do not copy Fincept branding, logo, trademarks, commercial copy, subscription mechanics, CR/credits, billing flows, or installer/runtime binaries.
- Do not read, copy, port, or adapt implementation source from
D:\FinceptTerminal\app\scriptsor any installed Fincept package source into executable paths. Use observed UI behavior, screenshots, JSON logs, public documentation, and independent implementation. - Live trading parity is in scope only through independently implemented, explicitly planned local modules. No live order path, private API key flow, real balance read, margin, leverage, short exposure, or derivatives execution may be reachable until a dedicated safety contract exists with local secret storage, explicit live-mode opt-in, confirmation gates, audit logs, kill switch behavior, and tests proving paper/live isolation.
- Keep all user data, layouts, logs, reports, backtests, screenshots, and settings local by default.
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.
- yesterday First seen · 62 lines · 1,366 tokens per session scan A 3828c14f5ee8
otto AGENTS.md is an instructions file published in the GitHub repository 0Smallcat0/otto (0 stars, last pushed 26d ago), licensed MIT. It adds 1,366 tokens to every session, about $0.0068 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
full-stack-ai-agent-template CLAUDE.md
Instructions for vstorm-co/full-stack-ai-agent-template, covering claude.md, project overview, commands, install dependencies and run tests.
full-stack-ai-agent-template AGENTS.md
Instructions for vstorm-co/full-stack-ai-agent-template, covering agents.md, project overview, commands, cli and architecture.
taskdog CLAUDE.md
Instructions for Kohei-Wada/taskdog, covering claude.md, project overview, monorepo structure, data storage & configuration and development commands.
python-samples-fastapi-restful CLAUDE.md
Instructions for nanotaboada/python-samples-fastapi-restful, covering claude.md, claude code, tech stack, structure and coding guidelines.
txtify CLAUDE.md
Instructions for lkmeta/txtify, covering txtify — agent guide, architecture (read this before touching job flow), commands, invariants & known traps and conventions.
mayak AGENTS.md
Instructions for LamantinAI/mayak, covering agents.md, quick start, common commands, validation and testing.