Borrowing it
Nothing to install: this file belongs to Southclaws/storyden. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Southclaws/storyden/main/.agents/skills/agent-builder/SKILL.mdgit clone --depth 1 https://github.com/Southclaws/storydenWrote 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/southclaws/storyden/agent-builder)<a href="https://agentmods.dev/skills/southclaws/storyden/agent-builder"><img src="https://agentmods.dev/badge/skills/southclaws/storyden/agent-builder/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/southclaws/storyden/agent-builder"><img src="https://agentmods.dev/badge/skills/southclaws/storyden/agent-builder.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 | $0.00040 | $0.00990 |
| Opus 5 | $0.00020 | $0.00495 |
| Sonnet 5 | $0.00008 | $0.00198 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
agent-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 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storyden Agent Builder
Use this skill when creating or improving a built-in Storyden Robot, its playbook, tool descriptions, tool schemas, or tool result shapes.
Built-in Storyden Robots run inside the Storyden ADK integration. They should be self-contained: do not require runtime web access, external skills, or documents unless a configured tool explicitly provides that capability.
Core Workflow
-
Define the Robot's job.
- State what user outcomes it owns.
- State what it must not attempt.
- Keep the scope narrow enough that the available tools can finish the workflow.
-
Map the workflow to tools.
- Prefer a few focused tools over many overlapping tools.
- Treat tool names, descriptions, inputs, outputs, and side effects as part of the Robot prompt.
- Move deterministic minutia into tools instead of telling the Robot to remember it.
-
Shape tool responses.
- Return high-signal fields in domain language.
- Include enough context for the next action.
- Add
messageandnext_actionfields when the result should steer the Robot. - Hide implementation trivia unless it changes what the Robot should do.
- Make errors actionable and specific.
-
Write the playbook.
- Define stages: discover, plan, edit/act, validate, deliver.
- Define when to ask versus act.
- Define authoritative tools for facts and side effects.
- Define failure behavior and user-facing language.
- Keep external references distilled locally; runtime Robots may be network-restricted.
-
Add eval scenarios.
- Use realistic tasks with multi-step workflows.
- Include failure cases and repeated attempts.
- Verify both final outcome and tool path when tool choice matters.
- Review raw transcripts, not just final summaries.
Good Robot Instructions
Good instructions:
- Define the Robot's job in one concrete paragraph.
- Define boundaries and forbidden behavior.
- Define workflow stages in the order tools should normally be used.
- Explain when to ask a user versus making a reasonable choice.
- Tie tool names to domain jobs, not internal implementation details.
- Define what success looks like.
- Define failure behavior in user-facing language.
- Keep the Robot from seeing implementation distractions that tools can handle.
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 · 119 lines · 40 tokens per session scan A 7f84ab0b9a4f
agent-builder is a skill published in the GitHub repository Southclaws/storyden (335 stars, last pushed 2d ago), licensed MPL-2.0. It adds 40 tokens to every session and 990 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
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.