san AGENTS.md

san AGENTS.md is an instructions file for Codex, OpenCode from genai-io/san. It costs 676 tokens per session, scanned A, original, Apache-2.0.

A repository guide and set of instructions for coding agents working on the San project. It explains where the main code, documentation, architecture notes, package map, and development commands are located.

In plain words
What is it for?
Use it to navigate San, find relevant documentation, understand package ownership and dependency rules, and follow the project’s development workflow.
Why use it?
It gives an agent the project’s layout and working rules before it changes code, reducing unnecessary searching and misplaced edits.

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/genai-io/san/agents-md
Clone the repo
git clone --depth 1 https://github.com/genai-io/san

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for san AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/genai-io/san/agents-md.svg)](https://agentmods.dev/instructions/genai-io/san/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/genai-io/san/agents-md"><img src="https://agentmods.dev/badge/instructions/genai-io/san/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 676 This file is loaded in full into every session.
When invoked 676 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 $0.00676 $0.00676
Opus 5 $0.00338 $0.00338
Sonnet 5 $0.00135 $0.00135
Haiku 4.5 $0.00068 $0.00068

Measured 4d ago against content hash 49bfa96d556b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

san 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 4d 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.

AGENTS.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

San Agent Guide

This file is the short navigation map for agents and contributors. Keep durable knowledge in docs/; keep this file focused on where to look and what rules to follow before changing code.

San follows the AGENTS.md standard, so this file is both the navigation aid for whoever opens the repository and the project instructions loaded into the running agent's context at session start. Keep it short: pointers and rules only. Uncommitted personal notes belong in AGENTS.local.md (git-ignored); a subdirectory with its own conventions can carry its own AGENTS.md, and the file nearest the working directory wins.

Start Here

  • Product overview: README.md
  • Documentation index: docs/index.md
  • Detailed architecture: docs/concepts/architecture.md
  • Package map and ownership: docs/reference/package-map.md
  • Dependency rules: docs/reference/dependency-rules.md
  • Feature notes: docs/packages/index.md
  • Development workflow: docs/operations/development.md

Repository Shape

  • cmd/san: CLI entrypoint and command wiring.
  • internal/app: Bubble Tea TUI shell, model composition, event routing.
  • internal/core: stable agent, message, tool, and system-prompt contracts.
  • internal/agent: agent construction and session-facing runtime setup.
  • internal/llm: model provider registry, clients, cost and logging helpers.
  • internal/tool: built-in tool registry, schemas, adapters, and executors.
  • internal/session: transcript persistence, projection, metadata, resume.
  • internal/task, internal/subagent, internal/cron: background work and orchestration.
  • internal/command, internal/skill, internal/plugin, internal/mcp, internal/hook: extension surfaces.
  • internal/setting, internal/persona: configuration and persona overlays.
  • internal/log, internal/secret, internal/filecache, internal/markdown, internal/confdir: infrastructure helpers.
  • internal/selflearn: background memory and skill review loop.
  • docs: durable explanations, design decisions, operations, and references.

Read the full file on GitHub · 66 lines

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. 4d ago First seen · 66 lines · 676 tokens per session scan A 49bfa96d556b

Subscribe to this mod's changes

san AGENTS.md is an instructions file published in the GitHub repository genai-io/san (76 stars, last pushed yesterday), licensed Apache-2.0. It adds 676 tokens to every session, about $0.0034 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.