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 skills add aaronnat23/disp8ch --skill lobster-workflowsgit clone --depth 1 https://github.com/aaronnat23/disp8chWrote 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.
[](https://agentmods.dev/skills/aaronnat23/disp8ch/lobster-workflows)<a href="https://agentmods.dev/skills/aaronnat23/disp8ch/lobster-workflows"><img src="https://agentmods.dev/badge/skills/aaronnat23/disp8ch/lobster-workflows/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aaronnat23/disp8ch/lobster-workflows"><img src="https://agentmods.dev/badge/skills/aaronnat23/disp8ch/lobster-workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00282 |
| Opus 5 | $0.00000 | $0.00141 |
| Sonnet 5 | $0.00000 | $0.00056 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
lobster-workflows 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 9d 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.
What it actually says
Lobster Workflows
Typed, deterministic multi-step pipelines with human approval gates and resumable execution tokens.
- Design workflows as linear pipelines: each step produces typed output consumed by the next step.
- Insert
wait-for-inputnodes at approval gates. Pass aresumeTokento allow humans to continue or cancel the workflow later. - Each pipeline step should be idempotent — if the workflow is resumed after approval, the step must produce the same result given the same input.
- Use
error-handlernodes around external API calls (email send, file write, webhook) to catch failures without aborting the entire pipeline. - Approval gate pattern:
claude-agent(classify/prepare) →wait-for-input(show classification to human) →if-else(approved?) →claude-agent(execute) →send-webchat(confirm). - Example: Email triage pipeline —
http_requestfetch inbox → classify messages by urgency →wait-for-inputto confirm batch → send replies → store sent log. - Store workflow state at each approval checkpoint in memory using type
eventwith the resume token as content. - For time-sensitive workflows: use
delaynodes between steps to pace execution and avoid overwhelming downstream services. - Track pipeline progress by emitting a
board-taskstatus update at each major stage.
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.
- 9d ago First seen · 14 lines · 0 tokens per session scan A fbd9e9eb565c
lobster-workflows is a skill published in the GitHub repository aaronnat23/disp8ch (100 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 282 tokens. 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.
Other skills, from other repositories
create-scraper
Given a careers page URL, uses Playwright browser tools to explore the page, identify reliable scraping patterns (preferring hidden JSON APIs over DOM scraping), then writes a TypeScript Scraper subclass for that company.
find-companies
Uses a public resource to retrieve a list of the current top tech companies, and detects whether they have listings on job boards with public APIs.
verify
How to run and drive this app to verify UI/server changes at runtime.
android-use
Control Android devices via ADB. Use when user asks to tap, swipe, type, launch apps, take screenshots, or automate Android device interactions.
agent-initialization
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.
update-setup
A one-time setup wizard for creating a personalised upgrade guide for a workspace. It checks for an existing guide, identifies the current version and installation clues, and requires confirmation of the installation method before writing a new guide.