snapref AGENTS.md

A set of contributor instructions for SnapRef, a local-first tool for browser automation. It documents commands, environment-variable rules, security boundaries, and runtime installation.

In plain words
What is it for?
Use it while contributing to SnapRef: run verification and self-tests, use the right SNAPREF_ settings, inspect the contract files, and keep private integrations out of the project.
Why use it?
It gives an agent project-specific rules to follow, reducing mistakes when changing or testing SnapRef. It also points to the preferred checks and documentation.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/nstranquist/snapref/agents-md
Clone the repo
git clone --depth 1 https://github.com/nstranquist/snapref

Made for: Codex, OpenCode.

Per session 169 This file is loaded in full into every session.
When invoked 169 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00169 $0.00169
Opus 5 $0.00084 $0.00084
Sonnet 5 $0.00034 $0.00034
Haiku 4.5 $0.00017 $0.00017

Measured yesterday against content hash c54c8506d0e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

snapref 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.

AGENTS.md · 24 lines

What it actually says

SnapRef — contributor notes

Local-first browser automation core. Public commands live on snapref.

Commands

make verify
make test-live
go run ./cmd/snapref version
go run ./cmd/snapref self-test
go run ./cmd/snapref demo mcp-policy
go run ./cmd/snapref demo ref-integrity

Rules

  • Use SNAPREF_* environment variables. Do not add factory-only names to this module.
  • Prefer README.md, SECURITY.md, and contract/ over whole-tree greps.
  • snapref self-test is the end-to-end engine check. Runtime downloads happen only through snapref runtime install.
  • Keep host adapters and private product handoffs out of this tree.
Changes

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.

  1. yesterday First seen · 24 lines · 169 tokens per session scan A c54c8506d0e3

Subscribe to this mod's changes

snapref AGENTS.md is an instructions file published in the GitHub repository nstranquist/snapref (0 stars, last pushed 12d ago), licensed Apache-2.0. It adds 169 tokens to every session, about $0.0008 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.