Borrowing it
Nothing to install: this file belongs to waittim/MemoryCustodian. 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/waittim/MemoryCustodian/main/GEMINI.mdgit clone --depth 1 https://github.com/waittim/MemoryCustodianWrote 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/waittim/memorycustodian/gemini-md)<a href="https://agentmods.dev/instructions/waittim/memorycustodian/gemini-md"><img src="https://agentmods.dev/badge/instructions/waittim/memorycustodian/gemini-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/waittim/memorycustodian/gemini-md"><img src="https://agentmods.dev/badge/instructions/waittim/memorycustodian/gemini-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 | $0.00240 | $0.00240 |
| Opus 5.5 | $0.00096 | $0.00096 |
| Sonnet 5.5 | $0.00048 | $0.00048 |
| Haiku 4.5 | $0.00024 | $0.00024 |
Grade A, and why
MemoryCustodian GEMINI.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 1mo 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.
What it actually says
@./skills/memory-custodian/SKILL.md
Agent Instructions
This repository builds MemoryCustodian: a local-first, pure-text project memory skill and CLI for coding agents.
MemoryCustodian
Before substantial work in this repository:
- Read
docs/memory/manifest.mdanddocs/memory/brief.md. - Choose a canonical task and supply touched/planned paths or an explicit area.
- Use strict routing before substantial work; stop on incomplete/invalid routing or unresolved conflicts.
- Do not infer areas/profiles from prose or load archive/inbox outside their explicit maintenance boundaries.
- After meaningful decisions or repeated corrections, update evidence-backed memory or propose an update.
Keep this file short. Do not import docs/memory/ files here; Gemini context files are loaded into prompt context, while MemoryCustodian should load project memory through the manifest at task time.
Development
- The CLI uses Python stdlib only.
- Run tests with
PYTHONPATH=cli python3 -m unittest discover -s tests. - Keep Skill instructions concise; put detailed policy in
skills/memory-custodian/references/.
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.
- 1mo ago Changed · +19 tokens per session 5eea72cd656f
- 1mo ago First seen · 24 lines · 221 tokens per session scan A ecf8cc193904
MemoryCustodian GEMINI.md is an instructions file published in the GitHub repository waittim/MemoryCustodian (25 stars, last pushed 29d ago), licensed MIT. It adds 240 tokens to every session, about $0.0010 per session on Opus 5.5. 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.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.