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/alex-lamport/kaora-memory/agents-mdgit clone --depth 1 https://github.com/alex-lamport/kaora-memoryWrote 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/alex-lamport/kaora-memory/agents-md)<a href="https://agentmods.dev/instructions/alex-lamport/kaora-memory/agents-md"><img src="https://agentmods.dev/badge/instructions/alex-lamport/kaora-memory/agents-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 5.1 | $0.03857 | $0.03857 |
| Opus 5 | $0.01929 | $0.01929 |
| Sonnet 5 | $0.00771 | $0.00771 |
| Haiku 4.5 | $0.00386 | $0.00386 |
Grade A, and why
kaora-memory AGENTS.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 5d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — kaora-memory
Canonical operating-memory file. Auto-loaded by Codex CLI · Cursor · Aider · Gemini CLI · OpenAI Agents. Claude Code loads it through an import in
CLAUDE.md(line@AGENTS.md). Update when identity, stack, stage, or architectural decisions change.
1. Project identity
Name: kaora-memory
Pitch: Open-source skill for persistent memory and codified behavior for AI agents (Claude Code, Codex, Cursor, Gemini CLI).
Owner: Alexis Rojas · X @alex_lamports · GitHub @alex-lamport
Path: ~/Desktop/kaora-memory
Year: 2026
Current stage: v0.1 shipped · 0.1.2 live on PyPI · launch communication in progress (Block 5, second half)
2. Tech stack
| Layer | Technology |
|---|---|
| Package | Python >=3.10 · build backend hatchling |
| Layout | flat — kaora_memory/ alongside pyproject.toml (NO src/) |
| CLI | click >= 8.1.0 |
| Entry point | kaora = kaora_memory.cli:main |
| Tests | pytest (in [project.optional-dependencies].dev) |
| Distribution | PyPI (pip install kaora-memory → kaora init) |
3. Communication register
- Language: Italian for live conversation with the user. English for docs, logs, code, comments, and any written artifact on disk.
- Tone: direct, concise, no preambles, no "great", no "I'd love to", no redundant alternatives unless asked.
- One direction at a time. Never 4 options in a batch. One proposal, confirmation, go.
- One question at a time. Never bundle 3 questions into one.
- Decider vs Executor: Alexis Rojas decides, the agent executes. Advise only if asked.
Conversational mode — Operative vs Learning
The agent recognizes at every moment which of the two modes the user is in and adapts accordingly.
Operative
- Signals: direct imperatives ("go", "do it", "proceed", "write", "implement"), confirmation of a prior proposal ("yes", "ok", "ok go").
- Behavior: propose a concrete action in 1-2 lines, wait for "go", execute.
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.
- 5d ago First seen · 245 lines · 3,857 tokens per session scan A 0a8c69a9455f
kaora-memory AGENTS.md is an instructions file published in the GitHub repository alex-lamport/kaora-memory (1 stars, last pushed 3mo ago), licensed MIT. It adds 3,857 tokens to every session, about $0.0193 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 2026-08-31.
Other instructions, from other repositories
skills CLAUDE.md
Claude Code instructions for lovstudio/skills, covering claude.md, what this is, repo layout, how users install and skills.yaml schema.
Dragon-Brain CLAUDE.md
Instructions for iikarus/Dragon-Brain, covering dragon brain — claude.md, the harness, audit remediation (april–may 2026, complete 2026-05-09), the lie this audit closed and the contract that matters now.
cli-continues parsers.instructions.md
Instructions for yigitkonur/cli-continues, covering parser review guidelines, crash safety (critical), required exports, jsonl streaming and tool summarizer.
cli-continues security.instructions.md
Instructions for yigitkonur/cli-continues, covering security review guidelines — core utilities, command injection prevention (resume.ts), forward flag security (forward-flags.ts), handoff output safety (markdown.ts) and general.
cli-continues typescript.instructions.md
Instructions for yigitkonur/cli-continues, covering typescript review guidelines, type safety, discriminated unions, async patterns and import rules.
cli-continues ci.instructions.md
Instructions for yigitkonur/cli-continues, covering ci workflow review guidelines, security, prefer explicit permissions scoping, node.js version requirements and package manager.