agentmods.dev

Adam AGENTS.md

Adam AGENTS.md is an instructions file for Codex, OpenCode from strangeadvancedmarketing/Adam. It costs 791 tokens per session, scanned A, original, MIT.

Repository instructions for AI coding agents working on the Adam Framework, a file-based memory and identity system for local AI assistants.

In plain words
What is it for?
Use them when modifying the Adam Framework, finding important paths, understanding its architecture, or contributing through an AI coding agent.
Why use it?
They explain the project structure and safety rules, including which files are templates and which contain live production memory.

Instructions file for CodexOpenCode

not rated 45 1mo ago A scan 791 tokens original MIT
View the source file strangeadvancedmarketing/Adam
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/strangeadvancedmarketing/adam/agents-md
Clone the repo
git clone --depth 1 https://github.com/strangeadvancedmarketing/Adam

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 Adam AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/strangeadvancedmarketing/adam/agents-md.svg)](https://agentmods.dev/instructions/strangeadvancedmarketing/adam/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/strangeadvancedmarketing/adam/agents-md"><img src="https://agentmods.dev/badge/instructions/strangeadvancedmarketing/adam/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 791 This file is loaded in full into every session.
When invoked 791 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 $0.00791 $0.00791
Opus 5 $0.00396 $0.00396
Sonnet 5 $0.00158 $0.00158
Haiku 4.5 $0.00079 $0.00079

Measured 5d ago against content hash c6b40820157b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Adam 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 5d 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 · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Instructions for AI Agents Working With This Repo

This file tells AI agents (Claude Code, Codex, Cursor, Copilot, etc.) how to work effectively with the Adam Framework repository.

What This Repo Is

The Adam Framework is a 5-layer persistent memory, coherence, and identity architecture for local AI assistants built on OpenClaw. It was developed over 8 months in production by a non-coder running a live business.

The core thesis: the memory is in the files. The model is just the reader.

Key Paths

engine/                    ← Gateway config + SENTINEL watchdog templates
vault-templates/           ← SOUL.md, CORE_MEMORY.md, BOOT_CONTEXT schema
tools/                     ← Python scripts: reconcile, coherence monitor, importer
docs/                      ← Architecture deep dives, proof, lessons learned
benchmarks/                ← Production benchmark data

Critical Rules for Agents

  1. Never touch live vault files. The templates in vault-templates/ are safe. The actual vault (wherever you installed it, e.g. ~/AdamsVault/) is production memory — do not read, modify, or reference real vault paths.

  2. Never commit secrets. SENTINEL.ps1 and openclaw.json contain API keys. The .gitignore blocks live versions. Templates use YOUR_API_KEY_HERE placeholders.

  3. The framework is local-first by design. Do not suggest cloud dependencies, hosted databases, or third-party memory services. Every component must run on the operator's machine with no external dependencies beyond the LLM API.

  4. Files are the memory. The Vault architecture uses human-readable Markdown. Do not suggest replacing this with databases, vector stores, or proprietary formats.

  5. Test against real sessions. tools/test_coherence_monitor.py runs against live JSONL session data. When modifying coherence_monitor.py, run the test suite.

Architecture Summary (for agent context)

Layer 1: Vault injection — SENTINEL loads identity files at every boot
Layer 2: memory-core plugin — live memory_search / memory_get mid-session
Layer 3: Neural graph — SQLite associative recall (nmem)
Layer 4: Nightly reconciliation — Gemini merges daily logs into CORE_MEMORY.md
Layer 5: Coherence monitor — scratchpad dropout detection + re-anchor injection

Read the full file on GitHub · 89 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. 5d ago First seen · 89 lines · 791 tokens per session scan A c6b40820157b

Subscribe to this mod's changes

Adam AGENTS.md is an instructions file published in the GitHub repository strangeadvancedmarketing/Adam (45 stars, last pushed 1mo ago), licensed MIT. It adds 791 tokens to every session, about $0.0040 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 contextai-agentidentity-sovereigntylocal-aiopenclawpersistent memory
Related

Other instructions, from other repositories

memsearch CLAUDE.md

Claude Code instructions for zilliztech/memsearch, covering claude.md, build & test commands, install in development mode, run a single test file and run a specific test.

zilliztech/memsearch · 2,349 tokens

graymatter AGENTS.md

AGENTS.md instructions for angelnicolasc/graymatter, covering agents.md, your tools, when to call which, first call and identity.

angelnicolasc/graymatter · 1,001 tokens

cortex-mem AGENTS.md

Instructions for sopaco/cortex-mem, covering cortex memory - ai agent context guide, project overview, core concepts, memory dimensions and three-tier layers.

sopaco/cortex-mem · 1,620 tokens

EGC CLAUDE.md

Claude Code instructions for Fmarzochi/EGC, covering egc: session memory protocol, at the start of every session, at the end of every session, parallel sessions and where state is stored.

Fmarzochi/EGC · 1,164 tokens

neurostack CLAUDE.md

Instructions for raphasouthall/neurostack, covering neurostack - claude code guide, quick reference, installation, mcp server (recommended for claude code) and openai-compatible api.

raphasouthall/neurostack · 3,464 tokens

EGC GEMINI.md

Gemini CLI instructions for Fmarzochi/EGC, covering egc: session memory protocol, at the start of every session, at the end of every session, where state is stored and mcp servers required.

Fmarzochi/EGC · 782 tokens