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/flytohub/flyto-core/agents-mdgit clone --depth 1 https://github.com/flytohub/flyto-coreWrote 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-core/agents-md)<a href="https://agentmods.dev/instructions/flytohub/flyto-core/agents-md"><img src="https://agentmods.dev/badge/instructions/flytohub/flyto-core/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 | $0.01121 | $0.01121 |
| Opus 5 | $0.00561 | $0.00561 |
| Sonnet 5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
flyto-core 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 5d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flyto-core Agent Rules
- Do not store credentials, PATs, cookies, bearer tokens, or account passwords in recipe YAML, tests, logs, or generated artifacts.
- Recipe credentials must be runtime parameters only. Do not put real secrets in defaults, examples, manifests, screenshots, or committed smoke reports.
- Before changing module registration, browser automation, recipe execution, or recipe bundle behavior, use flyto-indexer impact/search to understand callers.
- After changing recipes or recipe bundles, run the focused recipe bundle tests and a flyto-core recipe smoke.
- Before finishing any code change, run the relevant verify/test/smoke checks and record any skipped gate.
- Changes to Python source, routes, parsers, environment readers, recipes, or workflows must regenerate
docs/reference/and passpython scripts/check_documentation.py. - Public copy must use Flyto2 and only the approved
@flyto2.commailbox aliases; runpython scripts/check_brand_identity.py. - Install contributor dependencies with
pip install -e '.[dev]'; runtime integrations belong in explicit package extras. - Keep
.flyto-index/, run outputs, screenshots, and other generated artifacts out of commits.
The normal release closure is documented in docs/TESTING.md. At minimum run
the documentation and brand checks, audited-surface Ruff checks, the
non-browser/non-E2E suite, package build plus Twine validation, npm audit, and
strict full-scan Flyto2 Indexer verification.
Flyto2 Project Memory Contract
Every Flyto2 repository must keep this project-memory scaffold current:
AGENTS.md: agent operating rules, repo-specific constraints, verification commands.CLAUDE.md: Claude-facing handoff rules when this repo is edited outside Codex.PROJECT.md: product purpose, owned surfaces, users, and non-goals.ARCHITECTURE.md: module boundaries, runtime shape, data flow, and integration points.STATE.md: current status, known risks, release/deploy state, and last verification.ROADMAP.md: near-term, later, and explicitly out-of-scope work.tasks.md: actionable checklist with owners/status when known.DECISIONS.md: durable architectural/product decisions with dates and rationale.CHANGELOG.md: user-visible or operator-visible changes.docs/README.md: index for durable docs in this repo.workflows/*.md: repeatable agent workflows for idea capture, planning, implementation, bugfix, refactor, investigation, and wrap-up.handoffs/_registry.md: index of handoffs; new handoffs useYYYY-MM-DD-topic.md.
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.
- 5d ago First seen · 70 lines · 1,121 tokens per session scan A d7551098d4e6
flyto-core AGENTS.md is an instructions file published in the GitHub repository flytohub/flyto-core (480 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,121 tokens to every session, about $0.0056 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 2026-08-30.
Other instructions, from other repositories
apitap CLAUDE.md
Instructions for n1byn1kt/apitap, covering claude.md, using apitap as an mcp tool, commands, architecture and module map.
web-developer-mcp CLAUDE.md
Instructions for Artmann/web-developer-mcp, covering claude instructions for webdev mcp server, development guidelines, code style & organization, project structure and browser management.
qa-use CLAUDE.md
Instructions for desplega-ai/qa-use, covering claude.md, project map and tech stack.
pinchtab-mcp AGENTS.md
AGENTS.md instructions for maderwin/pinchtab-mcp, covering agent guidelines for pinchtab-mcp, key decisions (non-obvious), recommended workflow, when modifying tools and related projects.
GhostDesk CLAUDE.md
Claude Code instructions for YV17labs/GhostDesk, a project described as: Give any AI agent a full desktop — it sees the screen, clicks, types, and runs apps like a human. Automate anything with a UI: browsers, legacy software, internal tools. No API needed. One Docker command.
browsermcp-ext GEMINI.md
Instructions for derailed-dash/browsermcp-ext, covering browsermcp agent instructions, capabilities, limitations and usage.