Borrowing it
Nothing to install: this file belongs to flytohub/flyto-ai. 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/flytohub/flyto-ai/main/AGENTS.mdgit clone --depth 1 https://github.com/flytohub/flyto-aiWrote 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/flytohub/flyto-ai/agents-md)<a href="https://agentmods.dev/instructions/flytohub/flyto-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/flytohub/flyto-ai/agents-md.svg" alt="Measured on agentmods" 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 | $0.01499 | $0.01499 |
| Opus 5 | $0.00749 | $0.00749 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
flyto-ai 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 6d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flyto-ai Agent Rules
flyto-aiis the agent/runtime adapter between LLM providers, Flyto2 Cloud, blueprint learning, andflyto-coreMCP tools.- Do not store credentials, API keys, cookies, bearer tokens, screenshots containing secrets, or user passwords in source, tests, docs, handoffs, evidence, or generated YAML.
- Treat
flyto-coreas the module/runtime authority. Read its MCP schemas and recipes, but do not modifyflyto-corefrom this repo. - All
flyto-coreexecution must flow throughflyto_ai.tools.core_toolsso validation, browser retry, permission checks, and MCP evidence metadata stay consistent. - New agent capabilities need a closed loop: typed contract, guardrail, evidence/trace, test, docs, and rollback notes.
- Keep
.flyto-index/, transcripts, evidence, build output, local DBs, and eval results out of commits. - For deep changes, run flyto-indexer impact/search/verify before finalizing.
Coding Route Rules
- The public
code-mcp/code-serveservice is one audited entry. Host-owned lanes surround whichever implementer startup selected: a mandatory Indexer gate before any model edit and again after the source-controlled checks, a mandatory read-only Blueprint discovery lane, and Core validation. All four lanes are configured on every strict public route; none is detachable, and Blueprint and Core may resolve only applied or not-applicable. - Never let model prose assert that a lane, plan step, or gate ran. A lane outcome must come from a completed allowlisted call recorded in the route receipt.
- Do not add a route-bypass flag, do not let a green repository check stand in for the Indexer post-gate, and do not grant the implementer the audit tool, Blueprint execution authority, or Core danger/browser authority.
- Core execution keeps flowing through
flyto_ai.tools.core_tools. Do not import siblingflyto-core,flyto-blueprint, orflyto-indexersource. - Changing a lane, allowlist, bound, or receipt field is an architecture change:
update
ARCHITECTURE.md,docs/architecture-map.md,STATE.md, andDECISIONS.mdin the same change.
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.
- 6d ago First seen · 96 lines · 1,499 tokens per session scan A d88a1278b069
flyto-ai AGENTS.md is an instructions file published in the GitHub repository flytohub/flyto-ai (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,499 tokens to every session, about $0.0075 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.