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 JasonColapietro/suede-creator-skills --skill suede-clip-to-guidegit clone --depth 1 https://github.com/JasonColapietro/suede-creator-skillsWrote 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/jasoncolapietro/suede-creator-skills/suede-clip-to-guide)<a href="https://agentmods.dev/skills/jasoncolapietro/suede-creator-skills/suede-clip-to-guide"><img src="https://agentmods.dev/badge/skills/jasoncolapietro/suede-creator-skills/suede-clip-to-guide/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/jasoncolapietro/suede-creator-skills/suede-clip-to-guide"><img src="https://agentmods.dev/badge/skills/jasoncolapietro/suede-creator-skills/suede-clip-to-guide.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 | $0.00137 | $0.03645 |
| Opus 5 | $0.00068 | $0.01822 |
| Sonnet 5 | $0.00027 | $0.00729 |
| Haiku 4.5 | $0.00014 | $0.00364 |
Grade A, and why
suede-clip-to-guide 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 — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Suede Clip to Guide
Build one evidence-backed path from a video moment to a deeper written asset. Treat the clip as the attention layer and the guide as the authority layer. Do not assume the pattern performs; test the bridge against the account baseline.
Default Success Blueprint
Use this as the recommended pattern when the rights, source, claim, platform, and approval gates pass:
Useful guide with one promise
↓
Self-contained video moment
↓
Rights route + 8/10 moment score
↓
Clip hook + source credit + subtitles
↓
Post explains why the moment matters
↓
One explicit bridge to the guide
↓
Max Effort/Fleet: dual certainty gate
↓
Exact-content approval
↓
Public readback + clip-to-guide measurement
↓
Keep, revise, or stop from the observed result
Prefer this blueprint when:
- a guide already answers the natural next question created by the clip;
- the goal is deeper understanding, bookmarks, qualified replies, leads, or authority rather than raw views alone;
- the selected moment passes the 8/10 score and claim-support threshold;
- the rights route and current platform sequence are recorded;
- the account can observe at least one clip metric and one guide-transition or campaign metric.
Do not use it when:
- the guide is thin, unrelated, unpublished without a stable draft, or has no specific promise;
- the clip needs missing context, distorts the source, or exists only because it is popular;
- third-party reuse is blocked or the accountable fair-use decision is absent;
- the platform cannot preserve the source, clip, and guide bridge in a verified sequence;
- the idea is complete in the short post and the guide would add no depth.
For a first test, build three distinct packages only when three moments pass all gates. Compare them with the account's recent comparable posts. Keep the pattern only if the named guide-transition or campaign metric meets the decision rule; revise one variable at a time when it does not.
What ships with it
7 files 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 · 366 lines · 137 tokens per session scan A 1746b2c86508
suede-clip-to-guide is a skill published in the GitHub repository JasonColapietro/suede-creator-skills (135 stars, last pushed today), licensed MIT. It adds 137 tokens to every session and 3,645 once invoked, about $0.0007 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
skill-router
Use when a [skill-router] route card appears in the turn, when no card appeared on a non-trivial task, or when a route looks wrong. Routes every prompt to the right installed skill, pairs it with a process skill, tiers enforcement, and briefs sub-agents. 79 local skills + plugin skills indexed.
generate-report
Generate a comprehensive summary report of the latest experiment including metrics, plots, and comparison with baseline. Use this after training and evaluation to create a shareable experiment summary.
evaluate-model
Load the latest model checkpoint, run evaluation on the test set, and generate a metrics report with confusion matrix. Use this after training to assess model performance or to re-evaluate a specific checkpoint.
run-pipeline
Run the full data science pipeline: validate raw data, preprocess, engineer features, train model, and evaluate. Use this when you want to execute the end-to-end ML pipeline or re-run it after data or code changes.
api-test
Run API integration tests against the running backend, verify endpoints return expected responses and status codes. Use after deploying a preview or starting the dev server.
run-simulator
Build and launch the app in the iOS Simulator. Automatically selects an appropriate simulator device, boots it if needed, and installs and launches the app.