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 agentmods add skills/nicepkg/ai-workflow/tapestrynpx skills add nicepkg/ai-workflow --skill tapestrygit clone --depth 1 https://github.com/nicepkg/ai-workflowWrote 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/nicepkg/ai-workflow/tapestry)<a href="https://agentmods.dev/skills/nicepkg/ai-workflow/tapestry"><img src="https://agentmods.dev/badge/skills/nicepkg/ai-workflow/tapestry.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.03299 |
| Opus 5 | $0.00041 | $0.01649 |
| Sonnet 5 | $0.00016 | $0.00660 |
| Haiku 4.5 | $0.00008 | $0.00330 |
Grade C, and why
tapestry scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "$URL" | python3 -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
elif curl -sI "$URL" | grep -i "Content-Type: application/pdf" > /dev/null; then This is a copy
89% identical to learn-this — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tapestry: Unified Content Extraction + Action Planning
This is the master skill that orchestrates the entire Tapestry workflow:
- Detect content type from URL
- Extract content using appropriate skill
- Automatically create a Ship-Learn-Next action plan
When to Use This Skill
Activate when the user:
- Says "tapestry [URL]"
- Says "weave [URL]"
- Says "help me plan [URL]"
- Says "extract and plan [URL]"
- Says "make this actionable [URL]"
- Says "turn [URL] into a plan"
- Provides a URL and asks to "learn and implement from this"
- Wants the full Tapestry workflow (extract → plan)
Keywords to watch for: tapestry, weave, plan, actionable, extract and plan, make a plan, turn into action
How It Works
Complete Workflow:
- Detect URL type (YouTube, article, PDF)
- Extract content using appropriate skill:
- YouTube → youtube-transcript skill
- Article → article-extractor skill
- PDF → download and extract text
- Create action plan using ship-learn-next skill
- Save both content file and plan file
- Present summary to user
URL Detection Logic
YouTube Videos
Patterns to detect:
youtube.com/watch?v=youtu.be/youtube.com/shorts/m.youtube.com/watch?v=
Action: Use youtube-transcript skill
Web Articles/Blog Posts
Patterns to detect:
http://orhttps://- NOT YouTube, NOT PDF
- Common domains: medium.com, substack.com, dev.to, etc.
- Any HTML page
Action: Use article-extractor skill
PDF Documents
Patterns to detect:
- URL ends with
.pdf - URL returns
Content-Type: application/pdf
Action: Download and extract text
Other Content
Fallback:
- Try article-extractor (works for most HTML)
- If fails, inform user of unsupported type
Step-by-Step Workflow
Step 1: Detect Content Type
URL="$1"
# Check for YouTube
if [[ "$URL" =~ youtube\.com/watch || "$URL" =~ youtu\.be/ || "$URL" =~ youtube\.com/shorts ]]; then
CONTENT_TYPE="youtube"
# Check for PDF
elif [[ "$URL" =~ \.pdf$ ]]; then
CONTENT_TYPE="pdf"
# Check if URL returns PDF
elif curl -sI "$URL" | grep -i "Content-Type: application/pdf" > /dev/null; then
CONTENT_TYPE="pdf"
# Default to article
else
CONTENT_TYPE="article"
fi
echo "📍 Detected: $CONTENT_TYPE"
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.
- yesterday First seen · 482 lines · 81 tokens per session scan C 83f7d439834f
tapestry is a skill published in the GitHub repository nicepkg/ai-workflow (282 stars, last pushed 7mo ago), licensed MIT. It adds 81 tokens to every session and 3,299 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). It is 89% identical to learn-this, differing in 13 lines, and is treated as a copy.
Other skills, from other repositories
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
wukongim-cloud-analysis
Diagnose one exact live WuKongIM cloud Simulation Run or chat-lifecycle Cloud Lease through the repository Analysis MCP. Use when the user or a local Analysis Session asks Codex to inspect a run's cluster state, Prometheus signals, application logs, diagnostics, Controller task audits, profiles, or redacted config…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.