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/waittim/memorycustodian/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.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 | $0.00221 | $0.00221 |
| Opus 5 | $0.00111 | $0.00111 |
| Sonnet 5 | $0.00044 | $0.00044 |
| Haiku 4.5 | $0.00022 | $0.00022 |
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 4d 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.md. - Read
docs/memory/brief.md. - Load additional memory files only when the manifest says they are relevant.
- Do not load
docs/memory/archive/unless explicitly requested or performing memory maintenance. - After meaningful decisions or repeated corrections, update the appropriate memory file 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.
- 4d 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 (20 stars, last pushed 5d ago), licensed MIT. It adds 221 tokens to every session, about $0.0011 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.
Other instructions, from other repositories
ReMe AGENTS.md
AGENTS.md instructions for agentscope-ai/ReMe, covering agents.md, project principles, sources of truth, repository map and development setup.
scream-code AGENTS.md
AGENTS.md instructions for LIUTod/scream-code, covering scream-code development guide, workspace overview, packages, terminology and cross-package import rules.
framework AGENTS.md
AGENTS.md instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.
robrain AGENTS.md
Instructions for adelinamart/robrain, covering robrain — context management (oss self-hosted), session start (mandatory, first thing in every new chat), after every response (mandatory) and session end (last thing).
MindOS AGENTS.md
AGENTS.md instructions for GeminiLight/MindOS, covering agent 协作规则, 代码规范, spec 模板, spec and 目标.
hebb-mind CLAUDE.md
Instructions for afx-team/hebb-mind, covering hebb mind, priority hierarchy, project context, publication boundary and evaluation & benchmarks.