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 joao-aires/agent-skills-public --skill workflow-helpgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/workflow-help)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/workflow-help"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/workflow-help/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/joao-aires/agent-skills-public/workflow-help"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/workflow-help.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 | $0.00045 | $0.00474 |
| Opus 5.5 | $0.00018 | $0.00190 |
| Sonnet 5.5 | $0.00009 | $0.00095 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
workflow-help 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 yesterday.
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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow help
Explain the next useful activity
Read task guidance. Use its task catalogue and the client's observed skill/plugin inventory when available. If the stopping point is unclear, distinguish product direction, design/plan, implementation and assessment. Explain how to seek product discovery and prioritization expertise for an unresolved product problem, or develop when working software is requested; reuse accepted context for a defined feature or defect.
- Choose the activity whose stopping point matches the request. Explain what the user will have afterward: a product decision, requirements, a design, working code, or an assessment. This is more useful than presenting every activity as a compulsory sequence.
- Describe the expertise that would help with that work and identify an actual matching skill only after observing its availability. Explain which guidance supports the activity without expanding its scope.
- Give one or two copyable requests using syntax supported by the client. Include enough context to show the intended outcome and stopping point.
Explain availability and action boundaries
Distinguish installed/observed skills and tools from this package's catalogue and optional bundles; do not claim a tracker, MCP, browser or credential is available without evidence.
- Explain plugin-qualified commands where the client supports them, otherwise plain-language invocation; do not invent a universal alias or shell flag parser. The client's built-in help is separate.
- Cover explicit user/automation starts versus supporting guidance, interactive questions versus unattended blockers, and the current action policy.
- Help is read-only: do not run setup, probes, tests, installs, create schedules or begin the suggested activity.
- Link the usage/SDLC guides through their published URLs when useful.
A specialist can also be requested directly when available; selecting a discipline does not start a full lifecycle. Recommend the next activity without firing explicit-only skills, probing accounts or beginning work. Preserve the difference between catalogue entries and observed availability.
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.
- yesterday Changed · +14 lines 2ea584f4ff0a
- 2d ago Changed · +2 lines 676737ca02c4
- 7d ago First seen · 20 lines · 45 tokens per session scan A 09ce73bfcedd
workflow-help is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 474 once invoked, about $0.0002 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 2026-10-15.
Other skills, from other repositories
live-tutorial
Create an annotated MP4 tutorial from a workflow demonstrated in the owner's actual application. Use when asked for a tutorial video, not merely to watch an action live.
scaffold-exercises
A directory scaffold for course exercises, with sections, exercise folders, and optional problem, solution, or explanation versions. It creates the required Markdown files and checks the result with the repository's linter.
subscription-setup
A setup workflow for creating recurring medical-learning subscriptions after a doctor’s profile has been registered.
ArXiv
Search and retrieve arXiv academic papers by topic, category, or paper ID — with AlphaXiv-enriched AI-generated overviews. Uses arXiv Atom API across cs.AI/cs.LG/cs.CL/cs.CR/cs.MA/cs.SE/cs.IR. Three workflows: Latest, Search, Paper. USE WHEN arxiv, papers, latest papers, research papers, recent ML papers, paper…
Teach
Interactive voice-narrated tutorial on whatever the current conversation is about — teaches the topic beat by beat with ASCII diagrams in the terminal while speaking the actual lesson content aloud, asking one question per beat and quizzing until the ideas land. USE WHEN teach me, /teach-me, tutorial, teach me this…
explorer-interface-brief
Use when asked to design the interface for an interactive 3D explorer, plan a UI for exploring a 3D model of a topic, or write an image-model prompt for a 3D learning app mock-up. Produces, from a topic, the UI design brief (audience, layout, panels, interactions, label style, colour palette, accessibility) and an…