agentmods.dev

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.

In plain words
What is it for?
Use them when modifying Supamem, discovering its configuration, running checks, or understanding its memory and retrieval components.
Why use it?
They give an agent the project-specific rules needed to work safely and consistently in the repository.

Instructions file for CodexOpenCode

12 12d ago A scan 2,759 tokens original MIT
View the source file dzmitrys-dev/supamem
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/dzmitrys-dev/supamem/agents-md
Clone the repo
git clone --depth 1 https://github.com/dzmitrys-dev/supamem

Made for: Codex, OpenCode.

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. 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 $0.02759 $0.02759
Opus 5 $0.01380 $0.01380
Sonnet 5 $0.00552 $0.00552
Haiku 4.5 $0.00276 $0.00276

Measured 2d ago against content hash 8dfe6cb3f410, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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 · 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.

  1. 2d 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 (12 stars, last pushed 12d ago), licensed MIT. It adds 2,759 tokens to every session, about $0.0138 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.

Memory and contextPlanningTestingclaudecursoropencodetoken-savertoken-savingtoken-savings
Related

Other instructions, from other repositories

golembot CLAUDE.md

Instructions for 0xranx/golembot, covering golembot — project conventions for claude code, architecture hard constraints, things you must never do, interface change rules and file responsibility boundaries.

0xranx/golembot · 1,141 tokens

oh-my-openagent CLAUDE.md

Claude Code instructions for code-yeongyu/oh-my-openagent, a project described as: omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode.

code-yeongyu/oh-my-openagent · 3 tokens

golembot AGENTS.md

Instructions for 0xranx/golembot, covering assistant context, installed skills, directory structure and conventions.

0xranx/golembot · 522 tokens

awesome-copilot-id AGENTS.md

Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.

GulajavaMinistudio/awesome-copilot-id · 7,686 tokens

ai-rules-sync AGENTS.md

Instructions for lbb00/ai-rules-sync, covering agents instructions, project overview, tech stack, key features and directory structure.

lbb00/ai-rules-sync · 1,026 tokens

obsidianos_work AGENTS.md

Instructions for benoror/obsidianos_work, covering agents, skills, skill proxies (symlinks to .agents/skills/), rules and agent wrappers.

benoror/obsidianos_work · 2,627 tokens