Pinvou/pinvou-agent is an open-source desktop workspace where an AI agent helps with work, visual design, and software development. People use it to work with files and knowledge, create editable visual artifacts, connect coding agents to projects, and extend the workspace with tools, MCP servers, skills, and workflows; the catalogue skills add capabilities to that environment.
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 skills/pinvou/pinvou-agent/notesnpx skills add Pinvou/pinvou-agent --skill notesgit clone --depth 1 https://github.com/Pinvou/pinvou-agentWrote 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/skills/pinvou/pinvou-agent/notes)<a href="https://agentmods.dev/skills/pinvou/pinvou-agent/notes"><img src="https://agentmods.dev/badge/skills/pinvou/pinvou-agent/notes.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 | $0.00000 | $0.00508 |
| Opus 5 | $0.00000 | $0.00254 |
| Sonnet 5 | $0.00000 | $0.00102 |
| Haiku 4.5 | $0.00000 | $0.00051 |
Grade A, and why
notes 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.
What it actually says
IMA Notes
API base path: openapi/note/v1.
Use notes APIs when the user's real target is a note: search notes, list notebooks, list notes, read note content, create a new note, or append to an existing note.
Do not use shell commands or environment inspection for credentials. Call the native ima_openapi tool; credentials are never tool arguments.
Operations
- Search notes by title:
search_note - Search notes by content:
search_notewithsearch_type: 1 - List notebooks:
list_notebook - List notes:
list_note - Read note content:
get_doc_content - Create note:
import_doc - Append to existing note:
append_doc
Write Rules
- If the user says "create/new note", use
import_doc. - If the user says "append/add to existing note", use
append_doconly after the target note is clear. - For vague requests like "record this" or "save to notes", ask whether to create a new note or append to an existing note.
append_docis irreversible in normal user flow. Ask before modifying when there is any ambiguity.- Before
import_docorappend_doc, ensure all string fields are UTF-8. - Local image references are not supported in note content. Remove
file://, absolute local paths, and Windows local image paths from Markdown, then tell the user which image links were omitted.
Examples
{"api_path":"openapi/note/v1/search_note","body":{"search_type":0,"query_info":{"title":"会议纪要"},"start":0,"end":20}}
{"api_path":"openapi/note/v1/get_doc_content","body":{"note_id":"<note_id>","target_content_format":0}}
{"api_path":"openapi/note/v1/import_doc","body":{"content_format":1,"content":"# 标题\n\n正文"}}
Response Handling
IMA responses use { "code": 0, "msg": "...", "data": ... }. Treat code: 0 as success. For non-zero codes, show msg to the user and stop unless the next safe recovery step is obvious.
Do not expose note_id, folder_id, headers, Client ID, or API Key in normal user-facing answers.
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 · 47 lines · 0 tokens per session scan A 9516c3c5a652
notes is a skill published in the GitHub repository Pinvou/pinvou-agent (1,625 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 508 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 2026-08-30.
Other skills, from other repositories
self-optimizing-harness
Use the ResearchSwarm-backed self-optimizing harness to route a coding task, recall lessons from past sessions, and record outcomes so the agent compounds knowledge and improves over time. Trigger when starting a non-trivial task, when you want prior context, or after finishing work to capture what worked or failed.
knowledge-base
Build and maintain a company knowledge base as a wiki of interlinked markdown notes in the workspace — a private, compounding Wikipedia. Use when the user wants to start or organize a knowledge base / wiki, ingest sources (URLs, documents, pasted notes) into it, ask questions answered from it, or audit (lint) it.…
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
plur-session-end
Extract durable learnings at the end of a session. Saves corrections, preferences, and codebase patterns as engrams — nothing ephemeral, nothing sensitive.
plur-memory
Your memory stays on your machine. No cloud, no tracking, no API key. PLUR makes your OpenClaw remember — and shares that memory with every other tool you use.
remnic-memory-workflow
Shared memory workflow for Claude Code agents connected to Remnic — recall before acting, observe during work, remember at the end. Trigger phrases include "what do you remember about", "save this for later", "any context from last time".