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 45ck/skill-harness --skill demo-story-packagergit clone --depth 1 https://github.com/45ck/skill-harnessWrote 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/45ck/skill-harness/demo-story-packager)<a href="https://agentmods.dev/skills/45ck/skill-harness/demo-story-packager"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/demo-story-packager/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/45ck/skill-harness/demo-story-packager"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/demo-story-packager.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 | $0.00066 | $0.00523 |
| Opus 5 | $0.00033 | $0.00262 |
| Sonnet 5 | $0.00013 | $0.00105 |
| Haiku 4.5 | $0.00007 | $0.00052 |
Grade A, and why
demo-story-packager 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 11d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demo Story Packager
Overview
Use this skill to turn a captured demo into a reviewable and reusable package. Keep the durable source first and treat video, posters, frame strips, and HTML as generated outputs.
Inputs
.demo.yamlor equivalent source flowevents.json,verification.json,quality.json,environment.json- rendered
output.mp4and rawvideo.webm - analyzer outputs such as
review-bundle.json,review-prompt.md,video.shots.json,segment.evidence.json,layout-safety.report.json, andsegment-storyboard/ - screenshots, Playwright traces, or manual QA reports when they are part of the evidence
Workflow
- Identify the canonical source: usually
.demo.yaml, QA flow JSON, or a source artifact underdocs/artifacts/source/. - Inventory generated media and evidence. Do not infer pass/fail claims from video alone.
- Separate draft assets from approved assets. Keep generated assets out of git unless the repo intentionally promotes them.
- Write a handoff summary with audience, source path, run directory, evidence files, known quality findings, and next action.
- If a review surface is needed, use
demo-review-surfaceand record it indocs/artifacts/artifacts.manifest.jsonwhen the target repo has a manifest. - Before handoff, run available checks such as
demo-machine analyze,demo-machine doctor,node scripts/check-artifact-manifest.mjs, ornode scripts/check-artifact-html-policy.mjs.
Output Contract
Name these paths when available:
- source spec or QA flow
- run directory
- rendered media
- evidence files
- generated review surface
- approval or promotion destination
- commands already run
Guardrails
- Do not treat generated video as canonical evidence without source files.
- Do not include secrets, tokens, private browser data, or customer records in shareable media.
- Prefer local-first artifacts. Do not upload media to third-party services unless the user explicitly asks.
- If the source and media disagree, mark the package stale and regenerate from source.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 47 lines · 66 tokens per session scan A 0db268c73d95
demo-story-packager is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 523 once invoked, about $0.0003 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
typescript-providers
Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, and Claude Agent SDK. Use for provider-specific TS work; do not use for core-only changes.
potpie-source-ingestion
Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…
nature-data
Prepare, audit, or revise Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts. Use when the user asks about Nature data availability, research data sharing, repository selection, accession numbers, restricted or sensitive data, source data…
publication-chart-skill
This skill should be used when the user asks for a publication-quality scientific figure or table, wants help choosing the right chart for results, needs a paper-ready pubfig or pubtab workflow, wants a figure + companion table for a results section, wants an Excel sheet turned into publication-ready LaTeX, or wants…
obsidian-source-ingestion
Use this skill to ingest external materials into the current project-scoped Obsidian KB as source notes under Sources/Papers, Sources/Web, Sources/Docs, Sources/Data, Sources/Interviews, or Sources/Notes.
latex-conference-template-organizer
Organize messy conference LaTeX template .zip files into clean Overleaf-ready structure. Use when the user asks to "organize LaTeX template", "clean up .zip template", or "prepare Overleaf submission template".