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 librefang/librefang-registry --skill workflow-creatorgit clone --depth 1 https://github.com/librefang/librefang-registryWrote 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/librefang/librefang-registry/workflow-creator)<a href="https://agentmods.dev/skills/librefang/librefang-registry/workflow-creator"><img src="https://agentmods.dev/badge/skills/librefang/librefang-registry/workflow-creator/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/librefang/librefang-registry/workflow-creator"><img src="https://agentmods.dev/badge/skills/librefang/librefang-registry/workflow-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00030 | $0.02246 |
| Opus 5.5 | $0.00012 | $0.00898 |
| Sonnet 5.5 | $0.00006 | $0.00449 |
| Haiku 4.5 | $0.00003 | $0.00225 |
Grade A, and why
workflow-creator 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Composing Workflows with workflow_create
A workflow is a named, persisted sequence of steps that dispatches each step to an agent and threads the outputs together.
workflow_create registers one; workflow_run / workflow_start execute it afterwards, and it outlives the conversation that created it.
Decide whether a workflow is the right shape
Reach for workflow_create when the same multi-agent sequence is worth repeating, when it needs to be startable later by a cron job or another agent, or when the steps should run as a DAG rather than one long turn.
For something you will do once, message the agents directly with agent_send — a workflow you never run again is a name permanently taken on the daemon.
Call workflow_list before creating.
Names are unique across the daemon and the comparison is case-insensitive, so Deploy collides with an existing deploy.
A collision is rejected outright and nothing is overwritten; the error names the workflow that already holds the name.
The step shape
Every step requires name, agent, and prompt_template.
nameis unique within the workflow and is howdepends_onaddresses the step.prompt_templateis the text sent to the agent.{{input}}interpolates the previous step's output;{{whatever}}interpolates a declared input parameter or an earlier step'soutput_var.output_varstores this step's output under a name later steps reference as{{that_name}}. Without it, only the immediately following step can read the output, via{{input}}.depends_onlists step names that must finish first. A step may name one declared later in the array — execution is topological, not positional.timeout_secsis the wall-clock budget for the step: default 120, ceiling 3600.error_modeis"fail"(default, abort the run),"skip"(continue without this step's output), or{"retry": {"max_retries": 3}}. The retry form also acceptsbackoff_msandjitter_pct.modeis"sequential"(default),"fan_out"to run alongside the followingfan_outsteps, or"collect"to gather them. Richer nodes take a tagged object, such as{"conditional": {"condition": "APPROVED"}}.
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.
- 1mo ago First seen · 144 lines · 30 tokens per session scan A 1d5da56764e3
workflow-creator is a skill published in the GitHub repository librefang/librefang-registry (11 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 2,246 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-14.
Other skills, from other repositories
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output. Use when: (1) monitoring Claude/Codex sessions running in tmux, (2) sending input to interactive terminal applications, (3) scraping output from long-running processes inside tmux, (4) navigating tmux panes/windows…
agent-initialization
Initialize or extend an Agent from a user requirement - write AGENTS.md, set identity metadata, and create, install or import Skills and hook packages (scripts the harness runs on every prompt, before tool calls, or after a task). For an Agent with an in-app workbench, pair with penguin-plugin; for a standalone…
computer-history
Answer questions about what the user recently did on their computer — who contacted them, what they were working on, where they left off — by reading the local Computer History summaries and raw event streams.
ima-skill
A unified IMA skill for managing personal notes and knowledge bases through the platform's APIs.
notes
A note-management skill for searching, reading, creating, and adding content to personal notes in IMA, a note and knowledge platform.
cron
Use when the user asks to schedule recurring tasks, one-off reminders, timers, or cron-style jobs through the OpenSquilla cron tool.