Borrowing it
Nothing to install: this file belongs to holetexvn/memgw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/holetexvn/memgw/main/AGENTS.mdgit clone --depth 1 https://github.com/holetexvn/memgwWrote 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/holetexvn/memgw/agents-md)<a href="https://agentmods.dev/instructions/holetexvn/memgw/agents-md"><img src="https://agentmods.dev/badge/instructions/holetexvn/memgw/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.
<a href="https://agentmods.dev/instructions/holetexvn/memgw/agents-md"><img src="https://agentmods.dev/badge/instructions/holetexvn/memgw/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00984 | $0.00984 |
| Opus 5.5 | $0.00394 | $0.00394 |
| Sonnet 5.5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
memgw AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf http://127.0.0.1:8930/health # {"ok":true,...} How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memgw — instructions for AI agents
memgw is a shared long-term memory gateway for AI coding agents: one local store (SQLite + git) that Claude Code, Codex CLI, opencode, and any MCP client read from and write to. This file is for you, the agent, in two situations: installing memgw on your user's machine, or working on this codebase.
Installing memgw for your user
The wizard is non-interactive when stdin is not a TTY (or with --yes), so you can
run it directly:
npx @holetex/memgw setup --yes
What it does: creates ~/.memgw, generates auth keys, starts the gateway on
127.0.0.1:8930 (API) and :8931 (MCP), installs Claude Code hooks + MCP and Codex
MCP when those clients exist, and installs reboot supervision (launchd on macOS,
systemd --user on Linux; on Windows it prints the Task Scheduler command — run it).
Rules for you:
- The LLM key is the user's decision. Non-interactive setup skips the key, which
leaves memgw in capture-only mode — a safe default, nothing is lost: events queue
and get distilled retroactively once a key arrives. Tell the user this explicitly;
do not pressure them for a key. When they provide one:
(OpenAI, Anthropic, Groq, OpenRouter are recognised; the command also restarts the gateway so the key is live.) Never echo the key back, never commit it, never send it anywhere else.npx @holetex/memgw key "<key>" # provider auto-detected from the prefix - Verify, don't assume. After setup:
curl -sf http://127.0.0.1:8930/health # {"ok":true,...} npx @holetex/memgw doctor # every line should be ok (llm warns until a key is set) - Codex capture is a watcher process. Codex has no hooks. From a permanent
install on macOS/Linux,
setupinstalls the watcher supervised automatically (launchdcom.memgw.watch-codex/ systemdmemgw-watch-codex); on Windows or from the npx cache it prints the command — relay it to the user. Verify capture is really flowing withmemgw status("agents seen" must list a codex source after a Codex session). - Do not edit files under
~/.memgw/data/by hand — that is the memory store. Use the CLI (memgw save,memgw forget) or the MCP tools. - Per-client connection commands (opencode, claude.ai, Hermes, generic CLIs) are in docs/03-INTEGRATION.md; the setup wizard prints the ones it could not do automatically — relay those to the user instead of dropping them.
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 · 70 lines · 984 tokens per session scan A 2022c311da99
memgw AGENTS.md is an instructions file published in the GitHub repository holetexvn/memgw (3 stars, last pushed 2mo ago), licensed MIT. It adds 984 tokens to every session, about $0.0039 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.