skills/ectoclaw/SKILL.md
Cryptographic audit ledger and AI firewall for OpenClaw agents. Records every agent action (messages, skills, tools, plugins, memory, models) in an immutable hash-chained ledger with Ed25519 signatures and Merkle proofs. Policy engine for defining block, redact, flag, and approval rules. Exports compliance bundles and verification reports. Protects against prompt injection, credential theft, and unauthorized agent behavior.
npx skillsauth add bkohlberger/EctoClaw ectoclawInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
4 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Source code and install scripts are fully open-source at https://github.com/EctoSpace/EctoClaw.
When the user asks to see audit sessions, list recent sessions, or check audit history:
When the user asks to start a new audit, create a session, or begin tracking:
When the user wants to log an action, record an event, or track an operation:
When the user asks to verify a session or check chain integrity:
When the user asks about a specific session:
When the user asks to finalize, seal, or close an audit session:
When the user asks for metrics, statistics, or a summary:
When the user asks for a compliance report or Merkle proof:
When the user asks to prove a specific event exists in the chain:
When the user provides a Merkle proof to verify:
When the user asks for a full audit report:
When the user asks about active policies or what rules are configured:
When the user wants to set up audit rules:
When the user wants real-time monitoring:
When the user asks if EctoClaw is running:
Every OpenClaw lifecycle event is captured as a signed ledger entry:
| Event Type | What it captures | |------------------|-----------------------------------------------------| | MessageReceived | Inbound messages from any channel | | MessageSent | Outbound agent responses | | SkillInvoked | Skill activation with parameters | | SkillResult | Skill execution output | | ToolCall | Tool invocations (shell, file, http, browser) | | ToolResult | Tool execution results and observations | | PluginAction | Plugin lifecycle events | | ModelRequest | LLM API calls with prompt context | | ModelResponse | LLM responses | | MemoryStore | Memory write operations | | MemoryRecall | Memory read operations | | PolicyViolation | Blocked or flagged actions | | ApprovalRequired | Human-in-the-loop gate triggered | | ApprovalDecision | Human approval or denial recorded | | SessionSeal | Session finalized with Merkle root | | KeyRotation | Ed25519 signing key rotated |
Only send data to an EctoClaw instance you operate and trust. Treat audit logs as highly sensitive and protect them accordingly.
Every event is:
npm install ectoclaw
npx ectoclaw serve --dev
# Dashboard: http://localhost:3210/dashboard/
tools
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
tools
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
tools
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
tools
A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.