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 digital-stoic-org/agent-skills --skill clipgit clone --depth 1 https://github.com/digital-stoic-org/agent-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/digital-stoic-org/agent-skills/clip)<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/clip"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/clip/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/digital-stoic-org/agent-skills/clip"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/clip.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 6 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00000 | $0.01247 |
| Opus 5 | $0.00000 | $0.00624 |
| Sonnet 5 | $0.00000 | $0.00249 |
| Haiku 4.5 | $0.00000 | $0.00125 |
Grade A, and why
clip scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **curl/pandoc missing** → report; `pandoc` and `python3-bs4` are the only deps. How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GTD Clip
One URL → one note in /praxis/anti-library/articles/. The web copy may vanish; this one won't.
Steps
- Fetch + convert —
python3 <skill>/scripts/fetch-article.py "<url>" --out /praxis/.tmp/clip. Returns JSON (title, author, date, description, strategy, chars) and writesbody.md.chars< 2000 orstrategy: dom-densityon a known-long article → extraction is thin. Retry with WebFetch, or tell the user the page is paywalled/JS-rendered. Never fake a Dump.
- Read
body.md— you write the TLDR from the text, never from the metadata blurb. - Check for a duplicate:
Globthe articles folder on a distinctive title word. Existing note → update it, don't create a second. - Write
/praxis/anti-library/articles/<Titre exact>.md(flat folder — no year, no subject subfolder). Sanitize only/and:in the filename. - Clean up
/praxis/.tmp/clip, then report: path, tags, the TLDR, and one line on assets —assetsin the JSON counts the images without downloading anything:📎 6 images (2 encarts sponsors) — colle l'adresse de celle que tu veux garder.That line is the notification. Never render the list, never number it, never touch the note for it.
Assets — --attach
The human copies the asset's address from the article and passes it. That is the selection:
python3 <skill>/scripts/attach.py "<note.md>" <asset-url> [<asset-url> …]
Any asset, not just images — pdf, svg, csv, zip. It unwraps the CDN wrapper (full resolution, never
downscaled), saves as <slug>-NN.ext (extension from the URL, else from the served content-type),
then re-points the reference in # Dump: an image line becomes ![[…]] with the source URL in a
comment, an inline [label](url) becomes [[nom|label]] so the sentence survives. Anything absent
from the Dump is parked under # Notes rather than lost. Cap 25 MB — a guard, not a budget.
Never run it on your own initiative — not to "finish the job", not because the images look useful, not because the human said yes to an attachment earlier. No URL in hand, no byte fetched: there is no pre-download, no buffering "just in case", no fetching at clip time. The URL is the whole mandate.
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.
- 5d ago First seen · 98 lines · 0 tokens per session scan A 6ce97f8d118e
clip is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,247 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.