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 gylove1994/superpowers-deepseek-v4 --skill managing-samplesgit clone --depth 1 https://github.com/gylove1994/superpowers-deepseek-v4Wrote 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/gylove1994/superpowers-deepseek-v4/managing-samples)<a href="https://agentmods.dev/skills/gylove1994/superpowers-deepseek-v4/managing-samples"><img src="https://agentmods.dev/badge/skills/gylove1994/superpowers-deepseek-v4/managing-samples/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/gylove1994/superpowers-deepseek-v4/managing-samples"><img src="https://agentmods.dev/badge/skills/gylove1994/superpowers-deepseek-v4/managing-samples.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 | $0.00042 | $0.01072 |
| Opus 5 | $0.00021 | $0.00536 |
| Sonnet 5 | $0.00008 | $0.00214 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
managing-samples 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 10d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing Samples
When to invoke
This SKILL is strictly user-driven. Invoke it only when the user explicitly says one of:
- "Initialize the samples library" / "Seed the samples library" / equivalent
- "Add as a sample" / "Promote as exemplar" / equivalent
Do not invoke this SKILL:
- Automatically after a brainstorming or writing-plans session completes
- As a "would you like to save this as a sample?" prompt to the user
- Based on quality heuristics (convergence rounds, finding counts, etc.)
The user owns this library. The agent operates it on request.
Two workflows
Workflow 1: Initialization (one-time)
Used when the library is empty and the user wants to seed it from docs/superpowers/specs/ and docs/superpowers/plans/.
- Discover — list all
*.mdfiles underdocs/superpowers/specs/anddocs/superpowers/plans/. - Generate candidate metadata — for each discovered file, read its contents and produce a candidate YAML entry conforming to
index-entry-schema.md. Use your judgment ondomain,characteristics,problem_summary,why_exemplarbased on the file's content. - Present for user review — show all candidate entries in a table. Ask the user to confirm, edit, or skip each entry. Do not proceed until the user has acknowledged every candidate.
- Global conflict scan — invoke the
conflict-detection-prompt.mdin initialization mode (N×N) over all accepted candidates. Collect thepairsreport. - User batch resolution — for every reported pair, present the three-way choice (keep new+delete old / keep old+abandon new / keep both). Collect the user's decisions.
- Apply decisions — for each accepted candidate that survives, copy the source file from
docs/superpowers/specs/ordocs/superpowers/plans/into the correspondingsamples/specs/orsamples/plans/directory (preserve filename), and append its YAML block to the matchingINDEX.md. - Commit —
git add samples/ && git commit -m "feat(samples): seed initial sample library"
What ships with it
2 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.
- 10d ago First seen · 76 lines · 42 tokens per session scan A 625691908f6e
managing-samples is a skill published in the GitHub repository gylove1994/superpowers-deepseek-v4 (10 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,072 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 2026-08-31.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.