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 agentmods add skills/jimezsa/opencolab/workflow-buildernpx skills add jimezsa/opencolab --skill workflow-buildergit clone --depth 1 https://github.com/jimezsa/opencolabWrote 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/jimezsa/opencolab/workflow-builder)<a href="https://agentmods.dev/skills/jimezsa/opencolab/workflow-builder"><img src="https://agentmods.dev/badge/skills/jimezsa/opencolab/workflow-builder.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.01422 |
| Opus 5 | $0.00015 | $0.00711 |
| Sonnet 5 | $0.00006 | $0.00284 |
| Haiku 4.5 | $0.00003 | $0.00142 |
Grade A, and why
workflow-builder 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 3d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Builder Skill
Use this skill when the user wants to compose multiple agents into a repeatable workflow such as draft → review → judge, judge-and-retry, parallel reviews followed by a merge, or any other bounded coordination of agents.
This skill authors and operates workflows through the OpenColab CLI. It is not the workflow engine itself. The CLI/runtime owns parsing, execution, persistence, and human gate handling.
Source of truth
- Workflow definitions live at:
projects/<project_id>/workflows/<workflow_id>/workflow.xml - Workflow runs live at:
projects/<project_id>/workflows/<workflow_id>/runs/<run_id>/ - Each run folder contains
RUN.md(with YAML frontmatter),state.json,status.json,events.jsonl,inputs/initial.md, andsteps/<step_id>/.
Never edit state.json, status.json, or events.jsonl by hand. They are
written by the runtime.
Allowed step types
agent— runs one project agent with a generated prompt. Required:id,type="agent",agent,<prompt>. Optional:<output name="..." />.decision— runs one project agent and expects a strict<workflow-decision action="..." next="..." reason="..." />line in the response. Required:id,type="decision",agent,<prompt>,<choices>.human_gate— pauses the run for human input. Required:id,type="human_gate",<prompt>. Optional:allow="approve,stop,retry,edit,branch".merge— concatenates prior outputs into a single named value. Required:id,type="merge", at least one<input name="..." />,<output name="..." />.terminate— explicitly ends the run with a status ofsuccess,failed, orstopped.
Loops must be bounded
Every <loop> requires at least one of:
maxIterations="<n>"maxSteps="<n>"maxRuntimeMinutes="<n>"
Unbounded loops are rejected during validation.
Prompt references
Inside any <prompt> you can use template variables:
${input.<name>}— values supplied when starting the run.${<output_name>}— named outputs from prior steps (<output name="..." />).${<step_id>.output>— fallback reference for any step's raw output text.
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.
- 3d ago First seen · 159 lines · 30 tokens per session scan A 9237f6287ebb
workflow-builder is a skill published in the GitHub repository jimezsa/opencolab (11 stars, last pushed 20d ago), licensed MIT. It adds 30 tokens to every session and 1,422 once invoked, about $0.0002 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.
Other skills, from other repositories
gpt-researcher
GPT Researcher is an autonomous deep research agent that conducts web and local research, producing detailed reports with citations. Use this skill when helping developers understand, extend, debug, or integrate with GPT Researcher - including adding features, understanding the architecture, working with the API…
bilibili_search
Search for videos on Bilibili using keyword queries generated from user interests.
task-search
在框架预查的候选 bot 集里决出执行者(who)与协作方式(how),返回 4 态 SearchResult(HITSINGLE/HITGROUP/HITMULTIBOTS/MISS)。对齐案例剧本确定式映射。.
Deep Research
Produce a deep, structured research report on a topic: decompose into key dimensions, analyze each with evidence and reasoning, synthesize cross-cutting insights, and surface open questions. Use for deep research, analysis, and literature/landscape reviews.
vs-search-tuning
Use when a user asks an agent to evaluate or tune text search similarity for an existing Viking AI Search application and dataset.
vs-search
Search runtime and scene management: verify queries, inspect scenes, debug app readiness, and diagnose recall or scene-config issues.