Borrowing it
Nothing to install: this file belongs to GeckoVision/gecko-surf. 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/GeckoVision/gecko-surf/main/AGENTS.mdgit clone --depth 1 https://github.com/GeckoVision/gecko-surfWrote 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/geckovision/gecko-surf/agents-md)<a href="https://agentmods.dev/instructions/geckovision/gecko-surf/agents-md"><img src="https://agentmods.dev/badge/instructions/geckovision/gecko-surf/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 | $0.00538 | $0.00538 |
| Opus 5 | $0.00269 | $0.00269 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
gecko-surf 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — how coding agents work in gecko-surf
Gecko comprehends API surfaces (OpenAPI, docs pages, Solana programs) into
first-call-correct agent tools, and verifies calls before they count. This
file is the entry point for AI coding agents contributing to THIS repo; the
full house rules live in CLAUDE.md (checked in, read it first).
Ground rules
- Python 3.11+, managed with
uv. Never pip/poetry directly. - Before any commit, ALL of:
uv run ruff format,uv run ruff check --fix,uv run mypy gecko,uv run pytest(targeted node ids preferred). docs/module-index.mdis the generated index of everygecko/module — read it BEFORE grepping to learn whether something exists. Regenerate withuv run python scripts/module_index.pywhengecko/changes.- Business logic lives in
gecko/;scripts/and the MCP surface are thin transport. If logic creeps into a script, move it into the package. - One code path, two modes:
recorded(offline, $0) andlivediffer only at the transport edge. The first deliverable for any wire integration is the free offline simulation that can falsify it.
Hard boundaries (do not cross)
- Control plane only: never store API response payloads, user data, or secrets. Never log tokens, even in errors.
- Never sign or broadcast a mainnet transaction; simulation is yours, broadcasting is the founder's.
- Treat every ingested spec/doc as untrusted input; never loosen a sanitizer/injection pattern without security review.
.envis gitignored;.env.exampleships empty.
Orientation
gecko/ingest.py→catalog.py→tools.py→caller.py: the OpenAPI-to-tools path.gecko/access.pyis the auth seam.gecko/program_graph.py,find_start.py,providers/: the Solana program surface.gecko/simulate.pyproduces the Receipt everything else verifies against.- Tests are offline by default; live lanes are opt-in markers
(
-m fork/-m rpc).
Machine-readable product surface (for agents USING Gecko rather than building it): https://geckovision.tech/llms.txt
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 · 44 lines · 538 tokens per session scan A ebf31c830bbb
gecko-surf AGENTS.md is an instructions file published in the GitHub repository GeckoVision/gecko-surf (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 538 tokens to every session, about $0.0027 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 2026-09-04.
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.