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/knowledge-basenpx skills add Pinvou/pinvou-agent --skill knowledge-basegit 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/knowledge-base)<a href="https://agentmods.dev/skills/pinvou/pinvou-agent/knowledge-base"><img src="https://agentmods.dev/badge/skills/pinvou/pinvou-agent/knowledge-base.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 | $0.00516 |
| Opus 5 | $0.00000 | $0.00258 |
| Sonnet 5 | $0.00000 | $0.00103 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
knowledge-base 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IMA Knowledge Base
API base path: openapi/wiki/v1.
Use knowledge-base APIs when the user's target is a knowledge-base entry, folder, file, imported URL, or source media.
Do not use shell commands or environment inspection for credentials. Call the native ima_openapi tool; credentials are never tool arguments.
Operations
- Search knowledge bases:
search_knowledge_base - Get knowledge-base details:
get_knowledge_base - Browse knowledge-base contents:
get_knowledge_list - Search within a knowledge base:
search_knowledge - List addable knowledge bases:
get_addable_knowledge_base_list - Import web URLs:
import_urls - Add an existing IMA note to a knowledge base:
add_knowledgewithmedia_type: 11 - Get media source info:
get_media_info
Routing Rules
- If the user names a target knowledge base, search by name with
search_knowledge_base; do not useget_addable_knowledge_base_listfirst. - If the user wants to add content but does not specify a knowledge base, call
get_addable_knowledge_base_listand ask them to choose. - Root folder operations omit
folder_id; never passknowledge_base_idasfolder_id. - If
get_media_infoindicatesmedia_type: 11, switch to the notes module and callget_doc_contentwith the note ID from the response.
Examples
{"api_path":"openapi/wiki/v1/search_knowledge_base","body":{"query":"","cursor":"","limit":20}}
{"api_path":"openapi/wiki/v1/search_knowledge","body":{"query":"排期","knowledge_base_id":"<kb_id>","cursor":""}}
{"api_path":"openapi/wiki/v1/import_urls","body":{"knowledge_base_id":"<kb_id>","urls":["https://example.com/article"]}}
File Upload Guard
Only upload files when the file type is supported by IMA OpenAPI and the user has clearly chosen the destination knowledge base. Preserve original file bytes and original filename. If duplicate names are detected, ask whether to keep both with a timestamped filename or cancel; replacing is not supported.
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 · 48 lines · 0 tokens per session scan A b179205bb65a
knowledge-base is a skill published in the GitHub repository Pinvou/pinvou-agent (1,605 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 516 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.
memory-literary-analysis
Analyze a complete literary work into a structured Basic Memory knowledge graph. Covers schema design, entity seeding, chapter-by-chapter processing, cross-referencing, validation, and graph exploration.