lobsterLobster workflow runtime for deterministic pipelines with approval gates. Use when: (1) Running multi-step automations that need human approval before side effects, (2) Monitoring PRs/issues for changes, (3) Processing data through typed JSON pipelines, (4) Email triage or batch operations, (5) Any workflow that should halt and ask before acting. Lobster saves tokens by running deterministic pipelines instead of re-planning each step.
Install via ClawdBot CLI:
clawdbot install guwidoe/lobsterContribute: Source code & PRs welcome at github.com/guwidoe/lobster-skill
Workflow runtime for AI agents — typed pipelines with approval gates.
# Set alias (adjust path to your install location)
LOBSTER="node /home/molt/clawd/tools/lobster/bin/lobster.js"
# Or install globally: npm install -g @clawdbot/lobster
# Then use: lobster '<pipeline>'
# Run pipeline (human mode - pretty output)
$LOBSTER '<pipeline>'
# Run pipeline (tool mode - JSON envelope for integration)
$LOBSTER run --mode tool '<pipeline>'
# Run workflow file
$LOBSTER run path/to/workflow.lobster
# Resume after approval
$LOBSTER resume --token "<token>" --approve yes|no
# List commands/workflows
$LOBSTER commands.list
$LOBSTER workflows.list
| Command | Purpose |
|---------|---------|
| exec --json --shell "cmd" | Run shell, parse stdout as JSON |
| where 'field=value' | Filter objects |
| pick field1,field2 | Project fields |
| head --n 5 | Take first N items |
| sort --key field --desc | Sort items |
| groupBy --key field | Group by key |
| dedupe --key field | Remove duplicates |
| map --wrap key | Transform items |
| template --text "{{field}}" | Render templates |
| approve --prompt "ok?" | Halt for approval |
| diff.last --key "mykey" | Compare to last run (stateful) |
| state.get key / state.set key | Read/write persistent state |
| json / table | Render output |
# Monitor PR for changes (stateful - remembers last state)
$LOBSTER "workflows.run --name github.pr.monitor --args-json '{\"repo\":\"owner/repo\",\"pr\":123}'"
# Monitor PR and emit message only on change
$LOBSTER "workflows.run --name github.pr.monitor.notify --args-json '{\"repo\":\"owner/repo\",\"pr\":123}'"
When a pipeline hits approve, it returns:
{
"status": "needs_approval",
"requiresApproval": {
"prompt": "Send 3 emails?",
"items": [...],
"resumeToken": "eyJ..."
}
}
To continue:
$LOBSTER resume --token "eyJ..." --approve yes
# List recent PRs, filter merged, show as table
$LOBSTER 'exec --json --shell "gh pr list --repo owner/repo --json number,title,state --limit 20" | where "state=MERGED" | table'
# Get data, require approval, then process
$LOBSTER run --mode tool 'exec --json --shell "echo [{\"id\":1},{\"id\":2}]" | approve --prompt "Process these?" | pick id | json'
# Diff against last run (only emit on change)
$LOBSTER 'exec --json --shell "gh pr view 123 --repo o/r --json state,title" | diff.last --key "pr:o/r#123" | json'
YAML/JSON files with steps, conditions, and approval gates:
name: pr-review-reminder
steps:
- id: fetch
command: gh pr list --repo ${repo} --json number,title,reviewDecision
- id: filter
command: jq '[.[] | select(.reviewDecision == "")]'
stdin: $fetch.stdout
- id: notify
command: echo "PRs needing review:" && cat
stdin: $filter.stdout
approval: required
Run: $LOBSTER run workflow.lobster --args-json '{"repo":"owner/repo"}'
Lobster can call Clawdbot tools via clawd.invoke:
$LOBSTER 'clawd.invoke --tool message --action send --args-json "{\"target\":\"123\",\"message\":\"hello\"}"'
Requires CLAWD_URL and CLAWD_TOKEN environment variables.
Lobster stores state in ~/.lobster/state/ by default. Override with LOBSTER_STATE_DIR.
Generated Mar 1, 2026
Monitor GitHub pull requests for changes and automatically notify teams when a PR requires review or has been updated. This workflow uses stateful diffing to only alert on new changes, reducing noise and ensuring timely code reviews.
Process incoming emails in batches, filter for specific keywords or senders, and require human approval before sending automated responses or forwarding to relevant departments. This ensures compliance and prevents accidental communication.
Extract order data from APIs, transform it into a standardized JSON format, and apply approval gates before updating inventory or triggering shipment notifications. This reduces errors in fulfillment processes.
Automatically scan transaction logs for anomalies, group results by risk level, and halt for manager approval before flagging suspicious activities. This integrates deterministic checks with human oversight for regulatory compliance.
Fetch user-generated content from social media platforms, filter for inappropriate material using predefined rules, and require moderator approval before taking actions like removal or warnings, ensuring consistent policy enforcement.
Offer Lobster as a cloud-based service with tiered pricing based on workflow complexity and usage volume. Provide managed state storage and integration support, targeting enterprises needing scalable automation with approval gates.
Provide consulting services to design and implement custom Lobster workflows for specific industries, such as finance or healthcare. Offer training, support, and tailored integrations with existing tools like GitHub or email systems.
Distribute Lobster as open-source software to build a community, while monetizing through premium features like advanced analytics, enterprise-grade security, and dedicated support. Encourage contributions and extensions via the GitHub repository.
💬 Integration Tip
Set up environment variables like CLAWD_URL and CLAWD_TOKEN for seamless integration with Clawdbot tools, and use workflow files for reusable, complex pipelines to save development time.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection