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 oaustegard/claude-skills --skill dunking-anonymouslygit clone --depth 1 https://github.com/oaustegard/claude-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/oaustegard/claude-skills/dunking-anonymously)<a href="https://agentmods.dev/skills/oaustegard/claude-skills/dunking-anonymously"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/dunking-anonymously/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/oaustegard/claude-skills/dunking-anonymously"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/dunking-anonymously.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 | $0.00125 | $0.01543 |
| Opus 5 | $0.00063 | $0.00772 |
| Sonnet 5 | $0.00025 | $0.00309 |
| Haiku 4.5 | $0.00013 | $0.00154 |
Grade A, and why
dunking-anonymously 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 today.
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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dunking anonymously
A quote-post delivers your whole audience to the original author. For an account with forty followers that is a pile-on whatever your caption said. This renders the post as an image instead, so the words can be quoted without the handle.
Idea from Luis Villa, who built the same feature for himself (https://bsky.app/profile/lu.is/post/3mv6ynbcjr62b). His render greys the identity out; this one blacks it out.
Procedure
python3 scripts/dunk.py https://bsky.app/profile/someone.bsky.social/post/3mv6...
Takes a bsky.app URL, an at:// URI, or handle/rkey. Writes <rkey>.png to
the working directory, prints the alt text to stdout, and writes <rkey>.json
holding the source URI for your own records. The source URI stays out of both
the image and the alt text.
| flag | effect |
|---|---|
--redact "phrase" |
blacks out a literal phrase, repeatable |
--stamp |
adds the rotated REDACTED stamp |
--show-date |
prints the post date in the footer |
--out PATH |
output path |
--width N |
image width, default 1200 |
Then read the rendered PNG, actually open it, and re-run with --redact for
anything in the body that identifies the author. This is the step
that gets skipped.
Deps are PIL and the standard library. DejaVu Mono ships with the container. The API call is unauthenticated, so it needs no token and leaves no trace in anyone's notifications. See README.md for the host fallback and network surface.
Redactions applied
Avatar, display name and handle become black bars. Every at-mention facet in the
body is blacked out, since a mention is a second person's handle and a strong
search key for finding the original. Embedded images, video, link cards and quoted
posts render as [image not shown] and friends rather than being fetched, since
an embedded image can carry a face, a location or a watermark.
Engagement counts are dropped. The date is dropped unless --show-date, because
a date plus one distinctive sentence narrows a search to a single post.
What ships with it
4 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.
- today First seen · 136 lines · 125 tokens per session scan A 7c3530164bf8
dunking-anonymously is a skill published in the GitHub repository oaustegard/claude-skills (148 stars, last pushed yesterday), licensed MIT. It adds 125 tokens to every session and 1,543 once invoked, about $0.0006 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 2026-09-12.
Other skills, from other repositories
superdesign
Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models. Use whenever the user wants to design a page, feature, flow, slide deck, or brand-new product; improve or reproduce existing UI; compare design results across top models; explore visual variants…
Linear
Managing Linear issues, projects, and teams. Use when working with Linear tasks, creating issues, updating status, querying projects, or managing team workflows.
chanlun-engine-skill
A Chinese-language stock-analysis skill based on Chan theory, a method for interpreting price-chart structures such as turning points and trading ranges.
youtube-summary
Summarize a YouTube video into structured notes — TL;DR, key takeaways, chapter-by-chapter breakdown, and reference links. Use when the user shares a YouTube URL (or invokes /youtube-summary ) and wants a summary, takeaways, transcript notes, or a write-up of a talk, lecture, or tutorial. Fetches the transcript and…
plangate
Use for any non-trivial task with 2+ open decisions/tradeoffs OR multiple implementation steps — instead of deliberating one question at a time in chat, write a structured plan to a file and let the user review it inline in vim with > Q: / > A: blockquote markers, then revise until agreed before touching any code.…
coinmarketcap
Expert assistant for CoinMarketCap Pro API — price quotes, listings, historical OHLCV, market metrics, Fear & Greed Index, CMC100/CMC20 indices, exchange data, DEX data, airdrops, trending, community sentiment. Covers 10+ endpoint categories across REST + MCP + x402 pay-per-call modes. Use when the user wants: current…