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 ShockRock2004/kamar-taj --skill wonggit clone --depth 1 https://github.com/ShockRock2004/kamar-tajWrote 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/shockrock2004/kamar-taj/wong)<a href="https://agentmods.dev/skills/shockrock2004/kamar-taj/wong"><img src="https://agentmods.dev/badge/skills/shockrock2004/kamar-taj/wong/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/shockrock2004/kamar-taj/wong"><img src="https://agentmods.dev/badge/skills/shockrock2004/kamar-taj/wong.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 | $0.00144 | $0.04918 |
| Opus 5 | $0.00072 | $0.02459 |
| Sonnet 5 | $0.00029 | $0.00984 |
| Haiku 4.5 | $0.00014 | $0.00492 |
Grade A, and why
wong 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 — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wong — end-of-day learning guidebook (formerly daily-log)
Turn a full day of Claude Code work (across every session and repo) into a single dated markdown file written as a teaching guide, so the user can genuinely learn the work: re-implement the code by hand, understand why each decision was made, and be able to explain how it works because they actually understand it.
The output is NOT a changelog. It is a beginner's textbook — written so simply and conversationally that someone with no software background could read it top to bottom and understand both what was done and why. Every technical term is defined in plain language the first time it appears; code stays technical but is wrapped in plain-English explanation. Depth and the "why" matter more than completeness of trivia. See the full Writing style — REQUIRED rules in step 4.
Step 0. Read the effort level from the command
The user may pass an effort level as the first argument: light, medium, or
heavy. If none is given, default to heavy. (They may also pass a date; a
YYYY-MM-DD token is the date, a light/medium/heavy token is the effort. Either
order, both optional. e.g. /wong medium, /wong light 2026-06-25.)
Effort controls token usage — it scales BOTH the digest size (via --effort on
the collector) AND how much you do while writing:
- light — cheapest. Document only the top 2–3 pieces of work. Do not
run
git show/extra file reads; rely on the digest + commit messages, and include at most one short code snippet total. Keep each section brief. Still produce the Git skills section, Slack summary, PDF, and upload. - medium — balanced. Document the top ~5 pieces. Pull real code (
git show) for only the 2–3 most important ones. Moderate depth. - heavy (default) — the full treatment described below: every distinct piece of work, pull real code for each, full depth.
Carry the chosen level through all steps.
Steps
1. Collect the day's raw material
Run the collector with the chosen effort (it reads every session transcript from disk, so it captures all concurrent/closed sessions, not just this one):
What ships with it
3 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 · 367 lines · 144 tokens per session scan A dae4b89fb2c1
wong is a skill published in the GitHub repository ShockRock2004/kamar-taj (4 stars, last pushed 1mo ago), licensed MIT. It adds 144 tokens to every session and 4,918 once invoked, about $0.0007 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
claude-students
Transforma una carpeta cruda de material de un parcial universitario (PDFs, DOC/DOCX, PPT, audios .ogg de WhatsApp, capturas) en un material de estudio polished y completo — HTML SOTA autocontenido + paquete de artefactos de NotebookLM (podcast en español, infografía, guía de estudio, briefing doc, mind map, quiz…
exam-study-guide
A study-guide builder for a completed exam chapter that has not yet passed its required checks. It creates a structured teaching checklist and, in full mode, a self-contained HTML and printable PDF guide with readable formulas, visible images, explanations, examples, and answers.
exam-cheatsheet
A compiler that turns completed exam notes, mistakes, mastered topics, and reference material into a traceable pre-exam cheat sheet. It can also make a print-ready PDF when visual output or printing is requested.
markpdf
Convert Markdown to premium-themed PDFs, slide decks (PPTX/PDF), styled HTML, and shareable links via the MarkPDF MCP server. Use when raw Markdown isn't enough — reports, pitches, academic papers, résumés, decks, printable docs.
especialista-em-instrucao-de-trabalho
Especialista em Instrução de Trabalho (IT). Use para detalhar como executar uma tarefa específica: passos granulares, imagens, parâmetros e segurança. Palavras-chave: instrução de trabalho, IT, tarefa, passo a passo, detalhamento, execução, segurança.
knowledge-summarize
Generate a TL;DR summary of a specific document or learning unit in the Knowledge base. Pulls chunks from pgvector and synthesizes via Claude Haiku. Use when the user wants a quick overview ('summary of lesson 5', 'TL;DR of this PDF', 'explain document X in one paragraph').