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/claude-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/claude-md)<a href="https://agentmods.dev/instructions/waittim/memorycustodian/claude-md"><img src="https://agentmods.dev/badge/instructions/waittim/memorycustodian/claude-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 | $0.00153 | $0.00153 |
| Opus 5 | $0.00077 | $0.00077 |
| Sonnet 5 | $0.00031 | $0.00031 |
| Haiku 4.5 | $0.00015 | $0.00015 |
Grade A, and why
MemoryCustodian CLAUDE.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 today.
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
Claude Code Instructions
This repository builds MemoryCustodian: local plain-text memory governance for coding agents.
MemoryCustodian
Default behavior:
- Read
docs/memory/manifest.mdanddocs/memory/brief.md, choose a canonical task, and expose touched/planned paths or an explicit area. - Use strict routing and stop substantial work on incomplete/invalid routing or unresolved conflicts.
- Never infer area/profile routes from prose or load archive/inbox outside explicit maintenance.
- Keep memory usage minimal.
- Suggest memory updates after decisions, repeated corrections, or rejected approaches.
- Never store sensitive or personal information unless explicitly requested.
Run tests with:
PYTHONPATH=cli python3 -m unittest discover -s tests
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.
- today Changed · +1 lines · +29 tokens per session e937d8a1a024
- 5d ago First seen · 20 lines · 124 tokens per session scan A f13fd8a7caea
MemoryCustodian CLAUDE.md is an instructions file published in the GitHub repository waittim/MemoryCustodian (20 stars, last pushed today), licensed MIT. It adds 153 tokens to every session, about $0.0008 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
framework AGENTS.md
AGENTS.md instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.
memory-bridge AGENTS.md
AGENTS.md instructions for jiabaobei/memory-bridge, covering agents.md — 记忆桥项目规约（ai 协作会话必读）, 版本与发布（硬性规则，所有者 2026-08-29 定）, 架构铁律 and 工程习惯.
supergraph AGENTS.md
AGENTS.md instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
elephant-agent copilot-instructions.md
Copilot instructions for agentic-in/elephant-agent, covering github copilot instructions, source of truth order, review priorities, harness-specific checks and validation expectations.
growmos AGENTS.md
Instructions for codician-team/growmos: This repository keeps a knowledge graph in .growmos/ (entities, typed relations, provenance, profiles, a journal). It is the shared world model that survives context windows. Treat it as memory you read at the start of work and write to as you develop. Zero-config commands.