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 sammcj/agentic-coding --skill extract-wisdomgit clone --depth 1 https://github.com/sammcj/agentic-codingWrote 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/sammcj/agentic-coding/extract-wisdom)<a href="https://agentmods.dev/skills/sammcj/agentic-coding/extract-wisdom"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/extract-wisdom/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/sammcj/agentic-coding/extract-wisdom"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/extract-wisdom.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Agent Snooping · line 4 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Rogue Agent · line 4 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00043 | $0.04657 |
| Opus 5.5 | $0.00017 | $0.01863 |
| Sonnet 5.5 | $0.00009 | $0.00931 |
| Haiku 4.5 | $0.00004 | $0.00466 |
Grade A, and why
extract-wisdom 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 — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wisdom Extraction
<skill-dir> in commands below is this skill's base directory, shown when the skill loads.
Workflow
Step 1: Identify Source and Acquire Content
Determine the source type and read the corresponding reference file:
- YouTube URL (contains youtube.com or youtu.be): Read
references/source-youtube.mdand follow its instructions. - Web URL or local file: Read
references/source-web-text.mdand follow its instructions.
Talk slide deck
When the source is a recorded talk or presentation, dispatch a background sub-agent once the output directory exists, then continue to Step 2 without waiting. Brief it to:
- Find the slide deck for this exact talk: same speaker, title and event. Check links in the source description or page first, then search. A deck from a different delivery of the talk doesn't count.
- Download it to
$TMPDIRand convert it to markdown with the best suited skill or tool available (e.g.pptx-to-mdfor PPTX,liteparseorpdffor PDF, fetching the page for web-hosted decks). Keep slide order and interpret charts and diagrams. - Save it to the output directory as
<source-title> - slides.md, with the deck URL on the first line. - Return the file path, or "no deck found" with the searches tried.
After acquiring the source content, return here for Step 2. If the user provided additional instructions about the level of detail or focus areas, apply those throughout the analysis.
Step 2: Analyse and Extract Wisdom
IMPORTANT: Avoid signal dilution, context collapse, quality degradation and degraded reasoning for future understanding of the content. Keep the signal-to-noise ratio high. Preserve domain insights while excluding filler or fluff.
Scale the analysis to the source
Length follows what the source carries, never the template.
- Include a section only when it adds claims the reader has not already seen. Drop Structured Breakdown, Insights & Commentary or Additional Resources when they would restate Key Insights or hold nothing.
- Short source (under roughly 1,500 words or 10 minutes of video): write One-Minute Read, Summary, Key Insights and Actionable Takeaways only, plus Notable Quotes when the source has them.
- Finish early rather than pad. When a section runs long, merge related claims and state them more generally.
- The user's instructions on length or focus override these defaults.
What ships with it
12 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.
- .gitignore 116 B
- CLAUDE.md 793 B
- references/build-ebook.md 1.2 KB
- references/source-web-text.md 2.9 KB
- references/source-youtube.md 3.2 KB
- scripts/transcribe.py 9.6 KB runs code
- scripts/wisdom.py 145 KB runs code
- styles/wisdom-epub.css 7.1 KB
- styles/wisdom-index.html 52 KB
- styles/wisdom-pdf.css 7.7 KB
- styles/wisdom-pdf.html5 343 B
- tests/test_frames.py 4.3 KB runs code
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 Changed · +11 lines 6fb87330e67c
- 11d ago Changed · -1 lines d51b37da1702
- 24d ago Changed · +19 lines 45643eb1fccf
- 1mo ago First seen · 357 lines · 43 tokens per session scan A 7112cd255fef
extract-wisdom is a skill published in the GitHub repository sammcj/agentic-coding (164 stars, last pushed 3d ago), licensed Apache-2.0. It adds 43 tokens to every session and 4,657 once invoked, about $0.0002 per session on Opus 5.5. 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
yann-lecun-debate
Sub-skill de debates e posições de Yann LeCun. Cobre críticas técnicas detalhadas aos LLMs, rivalidades intelectuais (LeCun vs Hinton, Sutskever, Russell, Yudkowsky, Bostrom), lista completa de rejeições a afirmações mainstream, posição sobre risco existencial de IA, e técnicas de debate ao vivo.
yann-lecun-filosofia
Sub-skill filosófica e pedagógica de Yann LeCun.
code-documentation-code-explain
You are a code education expert specializing in explaining complex code through clear narratives, visual diagrams, and step-by-step breakdowns. Transform difficult concepts into understandable explanations for developers at all levels.
playwright
Use when the task requires capturing or automating a real browser from the terminal.
eli5
Explain concepts in very simple terms suitable for a five-year-old.
transformer-attention
Use when reasoning about Transformer self-attention, multi-head attention, positional encoding, masked decoder attention, or why attention replaced recurrence/convolutions in sequence models; not for generic NLP or unrelated attention topics.