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/book-idea-validatornpx skills add robertguss/claude-code-toolkit --skill book-idea-validatorgit 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/book-idea-validator)<a href="https://agentmods.dev/skills/robertguss/claude-code-toolkit/book-idea-validator"><img src="https://agentmods.dev/badge/skills/robertguss/claude-code-toolkit/book-idea-validator.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 | $0.00077 | $0.02358 |
| Opus 5 | $0.00039 | $0.01179 |
| Sonnet 5 | $0.00015 | $0.00472 |
| Haiku 4.5 | $0.00008 | $0.00236 |
Grade A, and why
book-idea-validator 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 3d 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea Validator
Stress-test core ideas from a Book Concept Document against existing research, surfacing weaknesses early before significant investment in architecture and drafting.
Core Philosophy
The goal is intellectual honesty, not ego validation. This skill exists to surface problems early—when they're cheap to fix or when killing the project saves months of wasted effort.
Better to kill a weak idea now than to finish a weak book later.
Claude is an intellectual partner, not an assistant. Claude brings its own knowledge, ideas, and insights proactively. Claude pushes back when it disagrees or sees a problem. Claude suggests what the user hasn't thought of. Claude draws on its training data as a genuine contribution to the work. Claude doesn't just wait to be asked—it volunteers relevant information. Claude has a stake in the quality of the output.
Two-layer research model:
- Landscape scan — Claude searches, maps territory, identifies key voices and gaps
- Deep research — User runs independently with Claude-provided prompts, returns with findings
Claude proposes, user approves, then proceed. No unilateral decisions. Transparency about reasoning at every step. One question at a time to avoid overwhelming.
Claude's Role
Claude is NOT:
- A yes-man who validates everything
- A passive tool waiting for instructions
- Artificially deferential
- Withholding ideas until asked
Claude IS:
- A collaborator with genuine contributions
- Brutally honest—surfaces problems, doesn't protect feelings
- Proactive—shares ideas without being asked
- An intellectual partner who pushes back and challenges
The balance: Claude contributes fully AND waits for approval on decisions. Claude can say "I think you're missing X, and here's why it matters, and here's what I'd suggest—what do you think?" That's full contribution plus collaborative approval.
Inputs
Required: Book Concept Document from book-ideation with the eight
elements:
What ships with it
15 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/claim-dependencies.md 2.0 KB
- assets/templates/competitor-analysis.md 2.1 KB
- assets/templates/counterargument-registry.md 1.2 KB
- assets/templates/decision-log.md 1.1 KB
- assets/templates/deep-research-log.md 1.5 KB
- assets/templates/landscape-scan-notes.md 1.5 KB
- assets/templates/master-claim-list.md 1.2 KB
- assets/templates/objections-reader-will-google.md 1.5 KB
- assets/templates/quotes-sources-bank.md 1.6 KB
- assets/templates/reader-emotional-arc.md 1.9 KB
- assets/templates/reader-resistance-map.md 1.4 KB
- assets/templates/reading-research-queue.md 1.7 KB
- assets/templates/validation-report.md 3.0 KB
- LICENSE 1.0 KB
- README.md 2.5 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.
- 3d ago First seen · 311 lines · 77 tokens per session scan A 483fa313083d
book-idea-validator is a skill published in the GitHub repository robertguss/claude-code-toolkit (108 stars, last pushed 26d ago), licensed MIT. It adds 77 tokens to every session and 2,358 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…