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/zebbern/claude-code-guide/dev-guide-generatornpx skills add zebbern/claude-code-guide --skill dev-guide-generatorgit clone --depth 1 https://github.com/zebbern/claude-code-guideWhat 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 | $0.00059 | $0.02990 |
| Opus 5 | $0.00030 | $0.01495 |
| Sonnet 5 | $0.00012 | $0.00598 |
| Haiku 4.5 | $0.00006 | $0.00299 |
Grade B, and why
dev-guide-generator scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt update && sudo apt install -y xxx How it starts
The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Guide Generator
One topic → complete technical tutorial: Through a structured SOP workflow, transform a technical topic into a comprehensive tutorial covering prerequisites, environment setup, core steps, common error troubleshooting, and advanced topics — all accompanied by a cheatsheet.
Quick Start
The user simply provides a technical topic or operational goal, and the Agent automatically generates a complete tutorial following this workflow:
User: Help me write a Docker beginner's tutorial
Agent: [Outputs complete technical tutorial + Cheatsheet following the SOP workflow]
SOP Workflow
Phase 1: Topic Scoping & Audience Analysis
Goal: Define the tutorial's technical subject, target audience, and scope boundaries.
Steps:
- Parse the topic: Identify the core technology, operational goals, and expected deliverables from the user's input
- Ask clarifying questions (up to 4 key questions):
- What is the target audience's technical level? (Complete beginner / Some experience / Experienced developer)
- What operating system will the reader be using? (macOS / Windows / Linux / Any)
- What should the reader be able to do after completing the tutorial? (Specific deliverable)
- Are there any version or tech stack constraints?
- If the user asks to skip clarification, proceed with these default assumptions:
- Audience: Has basic programming experience but is unfamiliar with the topic technology
- Environment: Cover both macOS and Linux (note Windows differences where necessary)
- Goal: Be able to independently complete a minimal working example
Output: Tutorial metadata summary (topic, audience, objective, scope — no more than 150 words)
Phase 2: Prerequisites
Goal: List all knowledge and tools the reader needs before starting this tutorial, ensuring there are no knowledge gaps.
Steps:
- Dependency analysis:
- List all technical concepts involved in this tutorial
- For each concept, determine whether it should be "explained within the tutorial" or "assumed as prior knowledge"
- Decision rule: If explaining it would digress more than 200 words from the main topic, classify it as a prerequisite
What ships with it
1 file 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.
- yesterday First seen · 379 lines · 59 tokens per session scan B ba62723b31c1
dev-guide-generator is a skill published in the GitHub repository zebbern/claude-code-guide (4,596 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 2,990 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
exam-coach
Quiz and coach the user for the Anthropic Claude certification exams using this repository's blueprints and official exam guides. Use when the user asks to practice, be quizzed, drill a domain, take a mock exam, or prepare for the Associate, Developer, or Architect certifications.
offensive-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
offensive-osint-methodology
Structured OSINT methodology framework: target definition, source selection, collection workflows, data correlation, timeline reconstruction, and reporting. Use to guide systematic OSINT campaigns or teach OSINT methodology.
offensive-exploit-dev-course
Full exploit development course roadmap and syllabus: weekly topics, recommended reading, lab setup, and learning path from vulnerability classes through advanced exploitation. Use to structure exploit dev training or onboard new researchers.
cdb-scan
Map this codebase into project memory — a code graph of every symbol and how they connect, plus a written profile of stack, layout, conventions and workflows. Re-run any time to refresh both in place. Use when memory is newly installed on an existing project, or when the project has changed enough that the stored map…
offensive-fuzzing-course
Week 2 of the exploit development curriculum. Covers fuzzing methodology: target selection, corpus generation, coverage-guided fuzzing with AFL++/libFuzzer, structured fuzzing, and triage/deduplication. Use when setting up fuzz campaigns, selecting harness strategies, or triaging fuzzer output.