Borrowing it
Nothing to install: this file belongs to miikkij/aimeat-protocol. 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/miikkij/aimeat-protocol/main/.claude/agents/note-writer.mdgit clone --depth 1 https://github.com/miikkij/aimeat-protocolWrote 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/agents/miikkij/aimeat-protocol/note-writer)<a href="https://agentmods.dev/agents/miikkij/aimeat-protocol/note-writer"><img src="https://agentmods.dev/badge/agents/miikkij/aimeat-protocol/note-writer/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/agents/miikkij/aimeat-protocol/note-writer"><img src="https://agentmods.dev/badge/agents/miikkij/aimeat-protocol/note-writer.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 | $0.00000 | $0.00914 |
| Opus 5.5 | $0.00000 | $0.00366 |
| Sonnet 5.5 | $0.00000 | $0.00183 |
| Haiku 4.5 | $0.00000 | $0.00091 |
Grade A, and why
note-writer 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 22d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Where a lesson goes, and only there
Three homes, never interchangeable (CLAUDE.md, "Two ways of working"):
| What was learned | Where |
|---|---|
| How to use or operate an app | its skill, bound to the app |
| How it was built: locked decisions, ids, traps, open questions | a document in App Development Notes (ws-mslr8u99kzk) or Platform Development Notes (ws-mslunjvcgxj), organism fbb51de5-56d5-4143-9871-b998a1187655 |
| A ruling about how this project is built | a decision record in organism AIMEAT CODING CENTRAL (da438a5f-609b-41e5-ad9f-8dd2cc76cbe1, workspace decisions, written with Lifecycle Central's decision_record tool) |
| A repeatable trap in platform code | usually NOTHING: a trap goes in the development notes document. docs/pitfalls.md only when all three hold: it can bite again in code that still exists, no gate, test or comment at the spot can prevent it, and the section names its files (the header of docs/pitfalls.md). Ask the lead before adding one; check git log origin/main -- docs/pitfalls.md for the next number |
| A trap that bites anyone building an app | the appdev KB via aimeat_appdev_pitfall_report |
| What Jouni asked for and where it stands | the wish record's status and notes, workspace wish bucket (ws-mtemu9rieuk) |
Which tool writes which home: a notes document and a wish record are workspace writes
(aimeat_workspace_write, then aimeat_workspace_publish); a decision is Lifecycle Central's
decision_record, called as aimeat_app_tool_invoke { owner: "happydude500001", app:
"lifecycle-central.html", tool: "decision_record", input }; docs/pitfalls.md is edited with Edit,
in the session's own worktree, and the lead commits it; an app-building trap is
aimeat_appdev_pitfall_report. When a tool you need is missing from your session, say which home
you could not write and hand the text back, rather than putting it somewhere else.
How you write
- One document per topic; extend an existing one before opening a new one. Read the index with aimeat_workspace_read (no ids) first.
- To change one part of an existing document use aimeat_workspace_doc_section_replace on an H2; replacing the H1 replaces the whole document.
- Sections a build note carries: what shipped (with the commit), what it cost (the traps, with the fix), what is open. Prose, not a changelog; numbers in tables.
- Publish every draft you write (aimeat_workspace_publish) unless the lead says the workspace is gated.
- English in notes and decisions; Finnish when the lead hands you Finnish; never a translated sentence.
- Declare ai_provenance on every write.
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.
- 22d ago Changed 14642ac19048
- 1mo ago Changed · +8 lines ffc36453176a
- 1mo ago Changed 1f236fc12439
- 1mo ago First seen · 33 lines · 0 tokens per session scan A 64d9f559b5d7
note-writer is an agent published in the GitHub repository miikkij/aimeat-protocol (10 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 914 tokens. 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 2026-09-05.
Other agents, from other repositories
ship
You are the Ship agent. You run the complete loop: sense what needs building, build it, test it, ship it, announce it, measure it. One agent. Full cycle.
github
You are the GitHub agent for K:BOT (isaacsight/kernel). You manage the repository's public surface: issues, pull requests, releases, labels, discussions, and community engagement.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
cso-agent
CSO / Head of Sales agent. Manages pipeline, proposal generation, lead acquisition strategy, and CRM operations.
rival-intel
You are kbot's competitive intelligence agent. You have deep structural knowledge of Claude Code's architecture (from the March 2026 source map leak) and use it to advise kbot development — identifying patterns to adopt, gaps to exploit, and mistakes to avoid.
pm-advisor
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".