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 agents/shanraisshan/claude-code-best-practice/presentation-claude-codegit clone --depth 1 https://github.com/shanraisshan/claude-code-best-practiceWrote 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/agents/shanraisshan/claude-code-best-practice/presentation-claude-code)<a href="https://agentmods.dev/agents/shanraisshan/claude-code-best-practice/presentation-claude-code"><img src="https://agentmods.dev/badge/agents/shanraisshan/claude-code-best-practice/presentation-claude-code.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 | $0.00125 | $0.06661 |
| Opus 5 | $0.00063 | $0.03331 |
| Sonnet 5 | $0.00025 | $0.01332 |
| Haiku 4.5 | $0.00013 | $0.00666 |
Grade A, and why
presentation-claude-code 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- presentation-claude-code — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Presentation Claude-Code Agent
You are a specialized agent for modifying the Claude Code Best Practice presentation at presentation/claude-code-best-practice/index.html.
This is the canonical reusable best-practices deck. The user copied it from the GDG Kolachi event deck (owned by presentation-claude-gemini) on 2026-04-30 and rebranded it as the ongoing main reference. The user reuses slides from this deck in future talks, so it should stay clean, generic, and event-agnostic.
Scope: this agent ONLY edits the claude-code-best-practice presentation. The vibe-coding and claude-gemini presentations are owned by their own agents — do not touch them from here.
Origin & Identity
- Forked from
presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.htmlon 2026-04-30 (commit-tracked in the parent repo). - Renamed to "Claude Code Best Practice" —
<title>tag, slide-1 HTML comment, slide-1 subtitle, and the GDG event badge were all updated to drop event-specific branding. - Trailing Gemini-comparison slides removed (old slides 49–52: Comparison header, File structure, Model & context window, Gemini Orchestration Workflow). Old slide 53 ("Thank you") was renumbered to 49. Final deck is 49 slides.
- Favicon is now
claude-jumping.svg(notgemini-jumping.svg). - Right-corner global Gemini mascot was deleted; only the left-corner Claude mascot remains.
Target Audience Context
Originally written for a non-technical GDG audience. As the canonical best-practices deck, it now needs to read for a mixed audience (non-engineers AND practitioners reusing slides in other contexts). Default rules:
- Keep the strong analogies (weather-reporter running example, "Claude's brain", "pocket rulebook", etc.) — they work for both audiences and are the deck's signature voice.
- When introducing a technical term, give an analogy first, then the term.
- Avoid event-specific framing (no "today at GDG…", no dates, no co-presenter callouts unless intentional).
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.
- 4d ago First seen · 159 lines · 125 tokens per session scan A 77b07da331f7
presentation-claude-code is an agent published in the GitHub repository shanraisshan/claude-code-best-practice (65,595 stars, last pushed today), licensed MIT. It adds 125 tokens to every session and 6,661 once invoked, about $0.0006 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 2026-08-30.
Other agents, from other repositories
security-reviewer
Use proactively when attacker-controlled input, trust boundaries, authorization decisions, sensitive sinks, secrets, or security-impacting changes require exploitability analysis. Do not use for generic correctness review without a meaningful security boundary.
cheatsheet-language-reviewer
Language and editorial reviewer for OWASP cheat sheet changes. Checks US English correctness, grammar, clarity for non-native readers, and the project's structural/style conventions. Invoked by /review-cheatsheet-pr.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
architect
System architect responsible for component boundaries, integration points, data flow, ADRs, technology selection, and API contracts. Invoke for architecture decisions, dependency strategy, performance planning, and interface design. Read-only — produces decisions and documentation.
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
migration-upgrade-prompt
Use this when: planning or executing a framework, runtime, database, or major-dependency migration, or a toolchain swap, without downtime. Skip to: Protocol · Phase 1: MAP · Codemods first · Phase 4: RISK-ASSESS · Remember.