Borrowing it
Nothing to install: this file belongs to ajmichels/moneta-notes. 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/ajmichels/moneta-notes/main/CLAUDE.mdgit clone --depth 1 https://github.com/ajmichels/moneta-notesWrote 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/ajmichels/moneta-notes/claude-md)<a href="https://agentmods.dev/instructions/ajmichels/moneta-notes/claude-md"><img src="https://agentmods.dev/badge/instructions/ajmichels/moneta-notes/claude-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/ajmichels/moneta-notes/claude-md"><img src="https://agentmods.dev/badge/instructions/ajmichels/moneta-notes/claude-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 | $0.02149 | $0.02149 |
| Opus 5.5 | $0.00860 | $0.00860 |
| Sonnet 5.5 | $0.00430 | $0.00430 |
| Haiku 4.5 | $0.00215 | $0.00215 |
Grade A, and why
moneta-notes 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 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read README.md first for the full architecture and tool specs — this file is about how to build
it, not what to build.
docs/specs/ vs. docs/plans/
docs/specs/S0xx-*.mdare living documentation. They're the contract for what each subsystem does and why — update them in place as behavior changes (don't leave them describing stale behavior, and don't fork a new spec number for a change to something already specified).docs/plans/S0xx-*.mdare disposable. They're step-by-step execution checklists written for agentic implementation of a spec, not a reference anyone should need afterward — any rationale worth keeping belongs in the corresponding spec, not the plan. Checkbox state in these files isn't reliably maintained during implementation, so don't use it to judge completion — verify against the actual repo (does the code exist, does it match the spec, do the tests pass) instead.- Once a plan's spec is implemented and verified, delete the plan file. Keeping it around past that point only invites drift between plan and reality.
docs/*.md — user-facing guides
docs/installation.md, docs/usage.md, docs/usage-vectors.md, docs/usage-mcp.md,
docs/process-management.md, and docs/uninstallation.md are living documentation too, same rule as
docs/specs/: keep them in sync with actual behavior, don't let them drift. They're linked from the
README's "Documentation" table so they're the first thing a reader on GitHub reaches. docs/usage.md
was split three ways (core CLI / vectors CLI / MCP) specifically so a change to one surface only needs
reading and editing its own file, not the whole combined reference — update the relevant page(s), in
the same change, whenever you touch:
scripts/install.sh/scripts/uninstall.sh(steps, prompts, what gets created/removed) →docs/installation.md/docs/uninstallation.md.src/cli/main.js's command surface (new command, new/changed flag, changed output shape, excludingvectorsbelow) →docs/usage.md.src/cli/vectors.js's command surface (new/changedmnotes vectorssubcommand or flag) →docs/usage-vectors.md.src/cli/daemon.js,src/indexer/daemon.js's launchd wiring, orlaunchd/*.plist.template(daemon control, log file layout, rotation policy) →docs/process-management.md.src/mcp/tools.js's tool list (added/removed/renamed MCP tool) →docs/usage-mcp.md.
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 · +5 lines · +100 tokens per session 089efdc98fc2
- 1mo ago Changed · +2 lines · +54 tokens per session 644a54a22791
- 2mo ago First seen · 129 lines · 1,995 tokens per session scan A 4cbe9da3f607
moneta-notes CLAUDE.md is an instructions file published in the GitHub repository ajmichels/moneta-notes (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,149 tokens to every session, about $0.0086 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 2026-08-31.
moneta-notes CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| moneta-notes CLAUDE.mdajmichels/moneta-notes | Instructions file | 2 | 1mo ago | Apache-2.0 | A | 2,149 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |