MemWhale: Instructions file for Codex

AGENTS.md

MemWhale AGENTS.md is an instructions file for Codex, OpenCode from wuisabel-gif/MemWhale. It costs 718 tokens per session, scanned A, original, MIT.

A set of instructions for using MemoryWhale, a local SQLite-based terminal memory system. SQLite is a file-based database that stores the recorded commands, output, notes, and sessions on the machine.

In plain words
What is it for?
Recalling earlier build or environment failures, recording commands and fixes, and continuing work across agent sessions without uploading the data.
Why use it?
It helps an agent check whether a previous session already solved an error and preserve useful fixes for later sessions or machines.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex.

This is wuisabel-gif/MemWhale's own configuration. It tells Codex and OpenCode how to work on MemWhale itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MemWhale configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wuisabel-gif/MemWhale. 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/wuisabel-gif/MemWhale/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/wuisabel-gif/MemWhale

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 MemWhale AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wuisabel-gif/memwhale/agents-md/github.svg)](https://agentmods.dev/instructions/wuisabel-gif/memwhale/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/wuisabel-gif/memwhale/agents-md"><img src="https://agentmods.dev/badge/instructions/wuisabel-gif/memwhale/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.

agentmods 80×15 button for MemWhale AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/wuisabel-gif/memwhale/agents-md"><img src="https://agentmods.dev/badge/instructions/wuisabel-gif/memwhale/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 718 This file is loaded in full into every session.
When invoked 718 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00718 $0.00718
Opus 5 $0.00359 $0.00359
Sonnet 5 $0.00144 $0.00144
Haiku 4.5 $0.00072 $0.00072

Measured 9d ago against content hash f3ea716929da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

MemWhale 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 9d 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 · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding agents (Codex, Claude, etc.) working in this repo.

Use MemoryWhale as durable terminal memory

This project is a terminal-memory system — use it on yourself. It stores commands, exit codes, stdout/stderr, notes, and whole sessions in a local SQLite database so a future agent session, a different machine, or a different agent can continue from what already happened. Everything is local; nothing is uploaded.

Database: <data_local>/MemoryWhale/memorywhale.sqlite3 (~/.local/share/... on Linux, ~/Library/Application Support/... on macOS).

Recall before you act

Before debugging a build/environment error, check whether it was solved before:

mw search "linker cc not found"      # full-text recall across commands, output, notes
mw context --last-error              # the most recent failure, with its error tail

It shows prior matching runs and what was run right after a past failure (often the fix). Prefer a known-good fix over re-deriving it.

Record as you go

Log notable commands — especially a failure and the fix that worked:

mw-remember --cwd "$(pwd)" --exit-code "$?" \
  --stderr "<error output>" \
  --notes "project:<name> what / why" -- <command> [args]

Record an exploratory stretch as a whole session:

mw --notes "project:<name>"    # ...work...  then: exit  (wait for "recorded session #N")

Tag related work across terminals with the same project:<name> to group it.

Inspect

  • mw-view <id> — one memory as a local web page (with suggested next steps).
  • mw-serve — dashboard at http://127.0.0.1:7071/; includes /graph and project views.
  • mw-recover — import an interrupted session transcript that didn't save.

Repo conventions

  • Before changing behavior, read docs/architecture.md and place the change in Capture, Memory, Retrieval, or Interfaces. Keep integrations thin and do not introduce agent-specific behavior into core.
  • Before debugging, run a focused test and query MemoryWhale for a recurring failure. Record non-obvious fixes after they are verified.
  • The Cargo workspace lives at the repository root. The reusable retrieval crate is crates/memorywhale-core, CLI sources are in crates/mw-cli, the React frontend is in src, and src-tauri contains only the desktop shell.
  • Build every helper from the repository root with cargo build --release -p memorywhale-cli --bins. The binaries are mw, mw-remember, mw-run, mw-screenshot, mw-serve, mw-view, mw-recover, and mw-mcp.
  • macOS only: after copying a built binary, re-sign it (codesign --force --sign - <path>) or it gets Killed: 9. See DEBUG.md.
  • Full usage: docs/reference/cli.md. Setup/troubleshooting: DEBUG.md.

Read the full file on GitHub · 71 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. 9d ago First seen · 71 lines · 718 tokens per session scan A f3ea716929da

Subscribe to this mod's changes

MemWhale AGENTS.md is an instructions file published in the GitHub repository wuisabel-gif/MemWhale (67 stars, last pushed yesterday), licensed MIT. It adds 718 tokens to every session, about $0.0036 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.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,737 tokens