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.
npx agentmods add instructions/m-t-d-n/agentmemory-codex-windows/agents-mdgit clone --depth 1 https://github.com/M-T-D-N/agentmemory-codex-windowsWrote 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.
[](https://agentmods.dev/instructions/m-t-d-n/agentmemory-codex-windows/agents-md)<a href="https://agentmods.dev/instructions/m-t-d-n/agentmemory-codex-windows/agents-md"><img src="https://agentmods.dev/badge/instructions/m-t-d-n/agentmemory-codex-windows/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02120 | $0.02120 |
| Opus 5 | $0.01060 | $0.01060 |
| Sonnet 5 | $0.00424 | $0.00424 |
| Haiku 4.5 | $0.00212 | $0.00212 |
Grade A, and why
agentmemory-codex-windows 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentmemory — Agent Instructions
This repository is the independent AgentMemory for Codex on Windows
downstream. Public downstream releases use
package.json#agentmemoryDownstream.version; the package version,
src/version.ts, export schema, and plugin versions stay aligned to the
upstream AgentMemory compatibility line. Do not publish any @agentmemory/*
package from this repository.
Architecture
agentmemory is a persistent memory system for AI coding agents, built on iii-engine's three primitives (Worker/Function/Trigger). Everything goes through registerFunction/registerTrigger/sdk.trigger() — never bypass iii-engine with standalone SQLite or in-process alternatives.
- Engine: iii-sdk (WebSocket to iii-engine on port 49134)
- State: File-based SQLite via iii-engine's StateModule (
./data/state_store.db) - Build: TypeScript → ESM via tsdown, output to
dist/ - Test: vitest (
npm testexcludes integration tests)
Windows/Codex downstream profile
The portable upstream package behavior described below remains the default for
other hosts. The supported Windows/Codex build in
packaging/windows-codex/ adds the following host-specific operating settings:
- four managed Codex hooks (
SessionStart,UserPromptSubmit,Stop, andSessionEnd) capture normal main-agent user and final-assistant turns while excluding ambient UI, title/fork, and subagent traffic; - capability-scoped
local-qwenuses only a loopback OpenAI-compatible server for typed graph extraction; all other LLM features receive the noop provider, fallback providers remain disabled, and force-proxy prevents standalone writes; - writes, deletion, and derived-store provenance are exact-project scoped;
deliberate reads may use
*, and the managed user-prompt hook performs a bounded cross-project recall with current-project weighting and source labels; - Codex performs selective promotion through the official memory, lesson, and manual graph tools; provider-backed summary, consolidation, reflection, crystallization, and compression remain disabled while local Qwen may enrich the exact-project graph, a fair cursor-preserving deferred backlog retries one project batch at a time, and deterministic structural extraction stays available; and
- canonical data is installation state, not a generated build artifact. See
packaging/windows-codex/README.mdfor build, cutover, and retention rules.
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.
- 3d ago First seen · 168 lines · 2,120 tokens per session scan A 4604d66a2407
agentmemory-codex-windows AGENTS.md is an instructions file published in the GitHub repository M-T-D-N/agentmemory-codex-windows (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,120 tokens to every session, about $0.0106 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.
Other instructions, from other repositories
engraphis AGENTS.md
Instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, 0. read this first — two architectures live in one package, 1. commands, ── unified dashboard + memory inspector ── and 2. the v2 recall pipeline (where the real work is).
engraphis CLAUDE.md
Instructions for Coding-Dev-Tools/engraphis, covering claude.md, the one rule that prevents most mistakes, before you say "done" — run the canonical gate, slash commands available here and working style in this repo.
Binder AGENTS.md
Instructions for mpazik/Binder, covering binder, tech stack, monorepo structure, testing and development.
cli AGENTS.md
Instructions for konteks/cli, covering agent instructions, project overview, tech stack, repository layout and common commands.
mnemic CLAUDE.md
Claude Code instructions for dongtang3/mnemic: This project includes a project-level .mcp.json for the Mnemic memory MCP server.
mnemic AGENTS.md
AGENTS.md instructions for dongtang3/mnemic: Mnemic is a graph-backed long-term memory substrate for coding agents and LLM applications.