b-open-io/clawnet-cli
skills/clawnet-cli/SKILL.md
This skill should be used when the user asks to "work on the ClawNet CLI", "debug clawnet-paperclip-plugin", "explain ClawNet vault architecture", "fetch content from ORDFS", or "publish an agent or organization to the ClawNet registry". Reference for ClawNet CLI internals, architecture, and recent changes to the registry, vault, and publishing flow.
$ install --global
skillsauthnpx skillsauth add b-open-io/prompts clawnet-cliInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jul 15, 2026, 4:42 AM143.9s1 file scanned
SKILL.md
- name:
- clawnet-cli
- version:
- 0.0.33
- description:
- >-
ClawNet CLI
Vault Architecture (v0.0.33)
ClawNet CLI uses @1sat/[email protected] and @1sat/wallet-mac for key management. The old configureVault() helper and built-in se-helper binary have been removed.
The vault is composed from three pieces:
SecureEnclaveProviderfrom@1sat/wallet-mac— platform-specific Secure Enclave operations. Instantiated withSecureEnclaveProvider({ name: "ClawNet" }).FileVaultStoragefrom@1sat/vault— file-based vault entry storage.createVault(provider, storage)from@1sat/vault— creates the vault instance from a provider and storage backend.
import { SecureEnclaveProvider } from "@1sat/wallet-mac";
import { FileVaultStorage, createVault } from "@1sat/vault";
const provider = new SecureEnclaveProvider({ name: "ClawNet" });
const storage = new FileVaultStorage();
const vault = createVault(provider, storage);
ORDFS Directory Traversal (v0.0.32)
clawnet add fetches files via /content/{manifest}/{path} directory paths. ORDFS resolves _N refs and nested directories natively, so the CLI no longer needs to parse them manually. The old downloadDirectoryEntries function with manual _N parsing was removed.
Example fetch path:
https://ordfs.network/content/{manifestTxid}/src/index.ts
ORDFS handles the directory tree resolution server-side.
Organization Publishing
clawnet publish ORGANIZATION.md publishes organization packages with an agent hierarchy (roles, reporting structure).
The ORGANIZATION.md format uses YAML frontmatter with an agents: array:
---
name: my-org
agents:
- slug: lead-agent
role: lead
- slug: worker-agent
role: worker
reportsTo: lead-agent
---
Each agent entry supports:
slug— agent identifier (must match a published agent)role— the agent's role within the organizationreportsTo— slug of the agent this one reports to (establishes hierarchy)
Agent Publish with Icons
Agent .md files support an icon: field in YAML frontmatter. The icon URL points to an avatar image that is stored in the registry and served via the API.
---
name: my-agent
icon: https://example.com/avatar.png
---
Related Skills
b-open-io/claudex
tools
VerifiedTrustedCommunity
This skill should be used when a Claude Code session needs to keep working after Anthropic usage runs out, or when the user asks to run the Claude Code harness on GPT-5.6 Sol. Trigger phrases include "my Anthropic usage ran out", "I'm out of Claude usage", "usage limit reached, what now", "keep working on another model", "run Claude Code on GPT-5.6 Sol", "use GPT-5.6 Sol as the model", "set up claudex", "claudex isn't working", "route the harness through CLIProxyAPI", or "bill against my ChatGPT/Codex subscription". It stands up a local proxy so the Claude Code CLI runs on OpenAI's Codex backend as an escape hatch, and diagnoses that setup when it drifts. macOS + Homebrew.
14SKILL.mdUpdated Jul 17, 2026
b-open-io/visual-wayfinder
testing
VerifiedTrustedCommunity
This skill should be used when the user asks to "open Visual Wayfinder", "answer a Wayfinder ticket visually", "turn this decision into a configurator", "show Wayfinder choices as a dashboard", "prototype the Wayfinder questionnaire", or wants interactive choice cards, tradeoff controls, rankings, ranges, toggles, and consequence previews for one active Wayfinder decision. It wraps the Wayfinder skill and JSON Render; it never replaces the tracker or resolves more than the active decision.
14SKILL.mdUpdated Jul 16, 2026
b-open-io/visual-proposal
development
VerifiedTrustedCommunity
This skill should be used when the user asks to "make a visual proposal", "write this up so I can share it", "present these options visually", "diagram the trade-offs", "turn this plan into something reviewable", or requests a shareable design pitch, architecture proposal, RFC, options comparison, or visual roadmap for work that has not been built. It produces one self-contained, theme-aware HTML page led by grounded diagrams. Use visual-review instead for completed code changes; do not use this skill for internal task tracking.
14SKILL.mdUpdated Jul 16, 2026
b-open-io/plugin-settings
tools
VerifiedTrustedCommunity
This skill should be used when the user asks to "add plugin settings", "make a plugin configurable", "store per-project plugin configuration", "use settings.local.json", "create a plugin state file", "expose skill settings in Agent Master", or "add a skill interface". Distinguishes official Claude Code settings from project-owned configuration and documents bOpen Agent Master skill interface discovery.
14SKILL.mdUpdated Jul 16, 2026