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-social-cutgit 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-social-cut)<a href="https://agentmods.dev/skills/45ck/skill-harness/demo-social-cut"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/demo-social-cut/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-social-cut"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/demo-social-cut.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 | $0.00064 | $0.00514 |
| Opus 5 | $0.00032 | $0.00257 |
| Sonnet 5 | $0.00013 | $0.00103 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
demo-social-cut 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 12d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demo Social Cut
Overview
Use this skill to derive a polished short edit from a real captured flow. The edit plan must point back to the source run and evidence; it is not a free-form video editing brief.
Decision Rules
- Use
demo-machine editor a project-native render path when the run hasevents.json. - Use frame and screenshot based slideshow cuts when the strongest evidence is screenshots or storyboard output.
- Use FFmpeg/Remotion only as render mechanisms, not as the source of truth.
- Prefer no captions when the user asks for silent, hero, slideshow, or in-browser preview output.
- Keep narration and captions optional derivatives, never implicit defaults for a silent cut.
Edit Plan
Produce a concise plan with:
- source run directory and source spec
- target audience: review, docs, launch, social, portfolio, issue repro, or release note
- aspect ratio and duration target
- selected moments with evidence references
- output assets: MP4, GIF/WebP preview, poster frame, frame strip, or HTML review page
- render command or next command to run
- quality checks and known risks
Recommended Cut Types
hero-loop: 6-15 second silent loop for README, landing page, or app previewfeature-cut: 20-45 second focused clip of one capabilityrepro-cut: short evidence clip showing a bug or fix pathslideshow-reel: still frames, zooms, and transitions from screenshots/storyboardsrelease-recap: selected before/after or workflow moments for changelog review
Quality Checks
- Verify the source run is complete before editing.
- Check that UI text remains readable at the target aspect ratio.
- Avoid cuts that hide failed assertions, console/network failures, or layout safety warnings.
- For silent cuts, make state changes visually obvious through framing, cursor, timing, or title cards.
- If external assets are used, record license and source; otherwise keep the cut local-first.
Handoff
Return the edit plan and any generated paths. If rendering is not run, state the exact command and prerequisites.
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.
- 12d ago First seen · 51 lines · 64 tokens per session scan A 40ffcf94c830
demo-social-cut is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 514 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
do-it-architecture
Use when authority, ownership, contracts, dependency boundaries, migration, recovery, or structural deletion can change a design.
do-it-code-quality
Use when designing, changing, or debugging code to locate causal ownership and close the affected behavior.
do-it-core
Use when repository work needs a shared baseline for intent, facts, causal changes, and honest evidence.
do-it-decide
Use when uncertainty about a choice, plan, dependency, or handoff could materially change what gets built.
do-it-review
Use to assess requirements and implementation quality independently, or to resolve a batch of review findings.
do-it-skill-authoring
Use when creating or revising a do-it skill so its trigger and unique professional judgment are useful without prescribing ceremony.