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 commands/dr-code/tessera/show-user-guidegit clone --depth 1 https://github.com/dr-code/tesseraWhat 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 | $0.00008 | $0.00499 |
| Opus 5 | $0.00004 | $0.00249 |
| Sonnet 5 | $0.00002 | $0.00100 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
show-user-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Open the User Guide for the Claude Code Mastery Project Starter Kit.
Steps
-
Check for the HTML file at
docs/user-guide.htmlin the project root. -
Open in browser — try the GitHub Pages URL first, fall back to local file:
Primary (online):
https://thedecipherist.github.io/claude-code-mastery-project-starter-kit/user-guide.htmlFallback (local):
docs/user-guide.html -
Detect the environment and use the correct open command:
- WSL:
wslview <url> - macOS:
open <url> - Linux:
xdg-open <url>
- WSL:
-
Also mention the markdown version is available at
USER_GUIDE.mdin the project root for reading directly in GitHub or a text editor.
Detection Logic
# Detect platform and open URL
URL="https://thedecipherist.github.io/claude-code-mastery-project-starter-kit/user-guide.html"
LOCAL="docs/user-guide.html"
if grep -qi microsoft /proc/version 2>/dev/null; then
# WSL
wslview "$URL" 2>/dev/null || wslview "$LOCAL" 2>/dev/null || echo "Could not open browser. Visit: $URL"
elif [[ "$OSTYPE" == "darwin"* ]]; then
# macOS
open "$URL" 2>/dev/null || open "$LOCAL" 2>/dev/null || echo "Could not open browser. Visit: $URL"
else
# Linux
xdg-open "$URL" 2>/dev/null || xdg-open "$LOCAL" 2>/dev/null || echo "Could not open browser. Visit: $URL"
fi
Output
After opening, tell the user:
User Guide opened in your browser.
- Online: https://thedecipherist.github.io/claude-code-mastery-project-starter-kit/user-guide.html
- Markdown:
USER_GUIDE.md(project root)- Tip: Use
/helpto see all available commands at any time.
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 · 59 lines · 8 tokens per session scan A 0fa4a2e5d8cb
show-user-guide is a command published in the GitHub repository dr-code/tessera (1 stars, last pushed 21d ago), licensed MIT. It adds 8 tokens to every session and 499 once invoked, about $0.0000 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 commands, from other repositories
e2e
使用 Playwright 对 Web UI 进行端到端测试(支持视频录制、Trace 录制、控制台/网络日志捕获).
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
review
Compare a reference design against an implementation. Accepts Figma URL, image file, or browser URL as reference.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.