What is supamem AGENTS.md?

Repository instructions describe Supamem, a Python command-line tool that stores and retrieves project information for coding agents. They cover its architecture, setup, configuration, tests, and development commands.

Use them when modifying Supamem, discovering its configuration, running checks, or understanding its memory and retrieval components.

They give an agent the project-specific rules needed to work safely and consistently in the repository.

How dzmitrys-dev/supamem configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to dzmitrys-dev/supamem. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dzmitrys-dev/supamem/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/dzmitrys-dev/supamem

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dzmitrys-dev/supamem/agents-md/github.svg)](https://agentmods.dev/instructions/dzmitrys-dev/supamem/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/dzmitrys-dev/supamem/agents-md"><img src="https://agentmods.dev/badge/instructions/dzmitrys-dev/supamem/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dzmitrys-dev/supamem/agents-md"><img src="https://agentmods.dev/badge/instructions/dzmitrys-dev/supamem/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,759 This file is loaded in full into every session.

When invoked 2,759 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02759	$0.02759
Opus 5.5	$0.01104	$0.01104
Sonnet 5.5	$0.00552	$0.00552
Haiku 4.5	$0.00276	$0.00276

Measured 2mo ago against content hash 8dfe6cb3f410, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

supamem 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 2mo 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 · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — supamem

Operational guide for AI coding agents working in this repository. Project-agnostic dual-memory CLI for Claude Code, Cursor, and OpenCode.

Project Snapshot

Language: Python 3.12+
Build backend: hatchling
Package manager: uv
CLI entry: supamem → src/supamem/cli.py:main
Tests: pytest (config in pyproject.toml)
Lint/format: ruff (line length 100, target py312)
External deps: Qdrant 1.10+ (HTTP), MCP 1.13+, fastembed, langchain-text-splitters

Architecture

src/supamem/
├── cli.py              # Typer-based CLI dispatcher
├── console.py          # Shared Rich console + theme (single source of branding)
├── config.py           # Pydantic config schema (D-38)
├── config_io.py        # Discovery: project → user → defaults; merge order locked
├── doctor.py           # Health + drift report (Plan 80.6-11)
├── init.py             # Greenfield bootstrap (Plan 80.6-08)
├── migrate.py          # Brownfield migration paths (Plan 80.6-09)
├── mcp_server.py       # MCP server entrypoint
├── embedders/          # minilm, bm25 — pluggable via entry-points
├── indexer/            # chunker (markdown_header), manifest
├── retrieval/          # tuned_hybrid, dense, bm25 backends
├── eval/               # Bench runner + bundled goldens (Plan 80.6-12)
├── hooks/              # claude_code, cursor — per-client snapshot hooks
├── install/            # claude_code, cursor, opencode — config installers
├── share/              # Canonical artifact templates
└── stats/              # Welford counter for usage telemetry

Plugin Entry Points (D-48)

Four plugin groups in pyproject.toml. Third parties add backends without forking:

supamem.retrieval — tuned_hybrid, dense, bm25
supamem.embedder — minilm, bm25
supamem.chunker — markdown_header, transcript
supamem.reranker — mxbai_v2 (Phase 8)

Config Discovery (D-38)

Order: ./.supamem/config.toml (project) → ~/.config/supamem/config.toml (user) → share/default.toml (shipped). Merge is shallow; project wins.

Read the full file on GitHub · 173 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.

2mo ago First seen · 173 lines · 2,759 tokens per session scan A 8dfe6cb3f410

Subscribe to this mod's changes

supamem AGENTS.md is an instructions file published in the GitHub repository dzmitrys-dev/supamem (13 stars, last pushed 2mo ago), licensed MIT. It adds 2,759 tokens to every session, about $0.0110 per session on Opus 5.5. 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.

claude cursor opencode token-saver token-saving token-savings

supamem AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
supamem AGENTS.mddzmitrys-dev/supamem	Instructions file	13	2mo ago	MIT	A	2,759	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

supamem: Instructions file for Codex