Shared_Memory AGENTS.md

A set of AGENTS.md instructions for the Shared_Memory project. AGENTS.md is a file that tells coding agents how to work in a repository.

In plain words
What is it for?
Guiding an agent through Shared_Memory setup, operating rules, and the start of its first work phase.
Why use it?
It gives the agent project-specific rules for operating the framework, setting it up, and obtaining the source before the initial phase.

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/kanenasingreece/shared_memory/agents-md
Clone the repo
git clone --depth 1 https://github.com/KanenasInGreece/Shared_Memory

Made for: Codex, OpenCode.

Per session 22,404 This file is loaded in full into every session.
When invoked 22,404 The same file — it is already loaded in full.
Security scan F 4 findings. Scan, not verified.
Origin unknown 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 $0.22404 $0.22404
Opus 5 $0.11202 $0.11202
Sonnet 5 $0.04481 $0.04481
Haiku 4.5 $0.02240 $0.02240

Measured yesterday against content hash d131977b016b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade F, and why

Shared_Memory AGENTS.md scanned grade F with 4 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

That buys a user without sudo the run up to Phase 2, where they can read exactly which steps still

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

⚠ **`uv` must be reachable WITHOUT this agent's shell profile, or every invocation of the skill fails silently.** Every command in this phase (and in `SKILL.md`) runs `memory_bridge.py` **through `uv run`** — and the age

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$STAGE"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -L https://github.com/KanenasInGreece/Shared_Memory/archive/refs/tags/vX.Y.Z.tar.gz | tar xz
AGENTS.md · 1,123 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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 · 1,123 lines · 22,404 tokens per session scan F d131977b016b

Subscribe to this mod's changes

Shared_Memory AGENTS.md is an instructions file published in the GitHub repository KanenasInGreece/Shared_Memory (1 stars, last pushed yesterday), with no licence file. It adds 22,404 tokens to every session, about $0.1120 per session on Opus 5. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.