sage AGENTS.md

Repository instructions that require coding and project work to use SAGE, a command wrapper that records local command history and can reduce noisy terminal output. They also describe the sage-managed sections of the repository.

In plain words
What is it for?
Use them whenever working on the repository, including coding, debugging, documentation, file tasks, tests, and package commands; terminal commands must run through sage run --.
Why use it?
They make command use consistent and provide a record of terminal activity while preserving the project's required workflow.

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/psycgod/sage/agents-md
Clone the repo
git clone --depth 1 https://github.com/PsYcGoD/sage

Made for: Codex, OpenCode.

Per session 661 This file is loaded in full into every session.
When invoked 661 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 $0.00661 $0.00661
Opus 5 $0.00331 $0.00331
Sonnet 5 $0.00132 $0.00132
Haiku 4.5 $0.00066 $0.00066

Measured 2d ago against content hash a952c0dd5507, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sage 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.

AGENTS.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SAGE MANAGED BLOCK START

SAGE Integration - MANDATORY

When a user asks for any coding, repo, file, debugging, documentation, or project task, start through SAGE automatically. The user should not need to type sage.

First actions for normal repo work:

  • Use native file/search/edit tools normally.
  • Route every terminal command through the PyPI SAGE wrapper: sage run -- <command>.
  • For multi-line file writes/appends, use native Write/Edit tools. Do not use shell heredocs through sage run; heredocs are shell-specific and can fail through wrappers/monitors.

Route every shell command through SAGE. Do not run bare terminal commands.

Allowed wrapper:

  • sage run -- <command>

Rules:

  • Python: sage run -- python script.py
  • Packages: sage run -- npm install
  • Tests: sage run -- pytest
  • If the wrapper fails before the target command starts, stop and report the wrapper failure.

Why:

  • Tracks local command history for the user
  • Compresses noisy output before it reaches AI context
  • Captures safe proof metrics for token savings and ML prediction
  • Keeps raw commands and output local unless the user enables higher telemetry

Examples:

  • Wrong: python test.py
  • Correct: sage run -- python test.py
  • Wrong: git status
  • Correct: sage run -- git status

Example user request:

  • User: "Please help me with my general book in this folder"
  • Correct agent start: inspect/read/edit files with available native tools, then use sage run -- <command> only when a terminal command is needed.
  • Wrong agent start: bare python, git, npm, ls, or other terminal commands without SAGE.

Any spawned subagent must be given the same SAGE shell-wrapper requirement in its prompt.

SAGE MANAGED BLOCK END

SAGE Repository Instructions

Mandatory Shell Wrapper

SAGE is installed in this repository. Route every shell command through the PyPI SAGE wrapper:

sage run -- <command>

Examples:

sage run -- git status
sage run -- python -m pytest
sage run -- npm install

Read the full file on GitHub · 82 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. 2d ago First seen · 82 lines · 661 tokens per session scan A a952c0dd5507

Subscribe to this mod's changes

sage AGENTS.md is an instructions file published in the GitHub repository PsYcGoD/sage (10 stars, last pushed 29d ago), licensed MIT. It adds 661 tokens to every session, about $0.0033 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.