lobster

lobster is a skill for Claude Code, Codex from OpenCoven/coven. It costs 79 tokens per session (1,044 once invoked), scanned A, original, MIT.

A command-line workflow engine for running typed, repeatable pipelines with saved state and approval steps. A pipeline is a sequence of automatic data-processing tasks.

In plain words
What is it for?
Use it to run workflow files or inline pipelines that execute commands, filter or sort data, remove duplicates, transform fields, and render text.
Why use it?
It reduces repeated planning for multi-step jobs and can pause before actions that need human approval.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to run workflow files or inline pipelines that execute commands, filter or sort data, remove duplicates, transform fields, and render text.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/opencoven/coven/lobster
Install

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.

Any agent
npx skills add OpenCoven/coven --skill lobster
Clone the repo
git clone --depth 1 https://github.com/OpenCoven/coven

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for lobster

README.md
[![agentmods](https://agentmods.dev/badge/skills/opencoven/coven/lobster.svg)](https://agentmods.dev/skills/opencoven/coven/lobster)
Your own site
<a href="https://agentmods.dev/skills/opencoven/coven/lobster"><img src="https://agentmods.dev/badge/skills/opencoven/coven/lobster.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,044 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.01044
Opus 5 $0.00039 $0.00522
Sonnet 5 $0.00016 $0.00209
Haiku 4.5 $0.00008 $0.00104

Measured 8d ago against content hash 47c8d6b3cfdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

lobster 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 8d 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.

skills/lobster/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lobster — Workflow Shell

Typed, local-first pipeline engine. Deterministic execution, approval gates, persistent state. Saves tokens by replacing multi-step LLM re-planning with one-shot pipeline calls.

CLI

lobster '<pipeline>'                    # inline pipeline
lobster run path/to/workflow.lobster    # YAML workflow file
lobster run --file wf.lobster --args-json '{"key":"val"}'
lobster resume --token <token> --approve yes|no
lobster doctor                          # health check
lobster help <command>                  # per-command help

Pipeline Commands

Data flow

Command Purpose Example
exec Run OS command exec --json --shell 'echo [1,2]'
where Filter where 'status=OPEN'
pick Project fields pick 'title,author,url'
head First N items head --n 5
sort Stable sort sort --key updatedAt --desc
groupBy Group by key groupBy --key category
dedupe Remove dupes dedupe --key id
map Transform map --wrap items / map status=done
template Render text template --text '{{title}} by {{author}}'

Output

Command Purpose
json JSON output
table Table output

Control flow

Command Purpose
approve Halt for approval (--emit for non-TTY/tool mode)
state.get Read persistent state
state.set Write persistent state
diff.last Compare to last snapshot

Integrations

Command Purpose
clawd.invoke Call OpenClaw tool endpoint
gog.gmail.search Fetch Gmail threads
gog.gmail.send Send Gmail
email.triage Categorize + draft replies
llm_task.invoke Call LLM with typed payloads
workflows.run Run named workflow
workflows.list List available workflows

Pipe syntax

Commands are piped with |. Data flows as typed JSON arrays (not text).

Read the full file on GitHub · 118 lines

Changes

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.

  1. 8d ago First seen · 118 lines · 79 tokens per session scan A 47c8d6b3cfdc

Subscribe to this mod's changes

lobster is a skill published in the GitHub repository OpenCoven/coven (47 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 1,044 once invoked, about $0.0004 per session on Opus 5. 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.