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/hyper3labs/clawdrive/skillnpx skills add Hyper3Labs/clawdrive --skill skillgit clone --depth 1 https://github.com/Hyper3Labs/clawdriveWhat 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 | $0.00047 | $0.01862 |
| Opus 5 | $0.00023 | $0.00931 |
| Sonnet 5 | $0.00009 | $0.00372 |
| Haiku 4.5 | $0.00005 | $0.00186 |
Grade A, and why
clawdrive scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL <share-url>/manifest.json # load manifest Copies of this mod
1 near-identical copy found in the catalogue:
- clawdrive — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClawDrive
Agent-native local file storage with multimodal semantic search, shareable collections (pots), and a 3D browser UI.
Install
npm install -g clawdrive
Or run without installing: npx clawdrive <command>.
Skill install:
clawdrive install-skill # auto-detects your agent (Claude/Codex/Copilot)
clawdrive install-skill --agent claude # explicit agent target
clawdrive install-skill --project # install into current project instead of global
npx skills add hyper3labs/clawdrive # alternative: via skills.sh
Prerequisites
| Dependency | Install |
|---|---|
| Node.js 18+ | brew install node |
| ffmpeg | brew install ffmpeg |
| Gemini API key | Free at https://aistudio.google.com/apikey |
export GEMINI_API_KEY="your-key-here"
Quick Start
clawdrive serve --demo nasa # web UI + API on :7432 (downloads ~248 MB first run)
clawdrive serve --demo nasa --read-only # hosted demo, mutations blocked
clawdrive serve # start with your own workspace
Core Commands
clawdrive add ./docs ./photos # add files or directories
clawdrive add https://example.com # add a URL
clawdrive add --pot my-project . # add into a pot
clawdrive search "quarterly revenue" # text search
clawdrive search --image photo.jpg # cross-modal: find docs related to a photo
clawdrive search --file clip.mp4 # search by any media type
clawdrive pot create research # create a pot
clawdrive pot add research ./papers # add files to an existing pot
clawdrive get "README.md" # read a file by canonical name
clawdrive todo # list files missing summaries
clawdrive tldr "report.pdf" --set "Q3 financials summary"
clawdrive caption "photo.jpg" --set "Astronaut beside a rover on Mars"
clawdrive digest "report.pdf" # show/set longer markdown digest
clawdrive rename "old.txt" --set "better-name.txt"
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.
- yesterday First seen · 198 lines · 47 tokens per session scan A 0f394ced33c3
clawdrive is a skill published in the GitHub repository Hyper3Labs/clawdrive (5 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 1,862 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
vector-databases
Vector database operations — embed, store, search, and build RAG pipelines.
agentrq
Learn creating, scheduling tasks, workspaces, and collaborating with human operators on the AgentRQ platform. Lead colony of AI agents using AgentRQ MCP tools.
model-update
新增或更新 CCX 项目中的模型注册技能。适用于 Claude 与非 Claude 模型，覆盖能力表、路由白名单、基准映射、代码生成与验证。.
conductor-implement
Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.
bionic-decision-engine
Unified mathematical arbitrator for all resource allocation decisions — money, time, energy, relationships. Absorbs 46 decision protocols + 24 strategy protocols into one dense engine.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.