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/robertguss/claude-code-toolkit/ebook-discoverynpx skills add robertguss/claude-code-toolkit --skill ebook-discoverygit clone --depth 1 https://github.com/robertguss/claude-code-toolkitWrote 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/robertguss/claude-code-toolkit/ebook-discovery)<a href="https://agentmods.dev/skills/robertguss/claude-code-toolkit/ebook-discovery"><img src="https://agentmods.dev/badge/skills/robertguss/claude-code-toolkit/ebook-discovery.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 | $0.00072 | $0.01690 |
| Opus 5 | $0.00036 | $0.00845 |
| Sonnet 5 | $0.00014 | $0.00338 |
| Haiku 4.5 | $0.00007 | $0.00169 |
Grade A, and why
ebook-discovery 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.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ebook Discovery
Surface ebook ideas you didn't know you had. This is divergent/generative discovery ("what's here?") that feeds into Ebook Concept Development.
Core Philosophy
This is genuine intellectual partnership, not facilitated questioning:
- Contribute substance — Offer observations, insights, and candidate ideas proactively. Don't just ask questions.
- Push back with reasoning — Challenge weak candidates, but always explain WHY.
- One question at a time — Never overwhelm with multiple questions.
- Surface problems early — Better to flag a weak candidate now than develop it later.
- Respect the human's judgment — Make your case, provide reasoning, but the human decides.
- Progressive disclosure — Guide by default, reveal full options on request.
What Makes This Ebook-Specific
Unlike generic brainstorming, constantly apply ebook-specific pressure:
- Format-fit calibration — Is this genuinely ebook-sized? Too thin = blog post. Too thick = full book.
- Value density thinking — Ebooks are concentrated solutions. Every element must earn its place.
- Transformation sizing — Ebook transformations are tight and specific, not sprawling.
Session Flow
First Session
1. Orientation Question:
"Let me understand your starting point. Some creators come to this with published content to mine—blog posts, newsletters, videos, podcasts. Others have deep expertise that hasn't made it into published form yet. Honestly, both are rich territory for ebook discovery. Which sounds more like you?"
2. Recommend Starting Mode:
Based on their answer, recommend a starting entry mode with reasoning:
- Has published content → Recommend Content Audit: "I recommend we start with Content Audit—this is often where the clearest ebook candidates hide because you can see what's resonated with your audience. Does that feel right?"
- Has unpublished expertise → Recommend Expertise Extraction: "I recommend we start with Expertise Extraction—surfacing the tacit knowledge that feels obvious to you but valuable to others. Does that feel right?"
What ships with it
9 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.
- assets/templates/discovery-tracker-template.md 3.0 KB
- assets/templates/handoff-summary-template.md 1.7 KB
- references/candidate-assessment.md 11 KB
- references/content-transformation.md 10 KB
- references/discovery-anti-patterns.md 9.1 KB
- references/discovery-questions.md 9.1 KB
- references/entry-modes-guide.md 19 KB
- references/expertise-extraction-guide.md 11 KB
- references/prioritization-guide.md 13 KB
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 · 212 lines · 72 tokens per session scan A f85d626dd20b
ebook-discovery is a skill published in the GitHub repository robertguss/claude-code-toolkit (108 stars, last pushed 26d ago), licensed MIT. It adds 72 tokens to every session and 1,690 once invoked, about $0.0004 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 skills, from other repositories
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-edr-evasion
EDR evasion offensive checklist: hook unhooking (user/kernel), direct syscalls, PPID spoofing, process injection variants, AMSI bypass, ETW patching, memory encryption, and behavior-based evasion. Use when planning EDR bypass during red team engagements or researching AV/EDR evasion techniques.
offensive-mitigations
Security mitigation reference and bypass catalog: ASLR, DEP/NX, RELRO, stack canaries, CFI, sandboxing, seccomp. Covers both detection of enabled mitigations and known bypass techniques. Use when assessing target hardening or planning exploit mitigation bypasses.
offensive-exploit-development
Exploit development operational guide: environment setup, debugging workflow, PoC development lifecycle, writing reliable exploits, using pwntools/pwndbg, heap exploitation techniques, and weaponization considerations. Use when actively developing exploits or setting up an exploit dev environment.
offensive-tls-attacks
Comprehensive methodology for auditing and exploiting TLS/SSL implementations and misconfigurations across network services and mobile applications. Covers protocol downgrade attacks including POODLE (CVE-2014-3566) against SSLv3 CBC padding, DROWN (CVE-2016-0800) cross-protocol attack leveraging SSLv2 export ciphers…
offensive-advanced-redteam
Comprehensive red team operations methodology covering full engagement lifecycle from planning through reporting. Addresses engagement scoping and rules of engagement negotiation, multi-tier C2 infrastructure design with redirectors and domain fronting, malleable traffic profiles and beacon tradecraft, OPSEC…