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-architectnpx skills add robertguss/claude-code-toolkit --skill book-architectgit 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-architect)<a href="https://agentmods.dev/skills/robertguss/claude-code-toolkit/book-architect"><img src="https://agentmods.dev/badge/skills/robertguss/claude-code-toolkit/book-architect.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 | $0.00094 | $0.01801 |
| Opus 5 | $0.00047 | $0.00901 |
| Sonnet 5 | $0.00019 | $0.00360 |
| Haiku 4.5 | $0.00009 | $0.00180 |
Grade A, and why
book-architect 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Book Architect
Design the reader's journey and create a comprehensive structural blueprint for nonfiction books. Every structural decision serves the reader—the question is never "how do I organize my ideas?" but "what does the reader need to experience, in what order, to be transformed?"
Core Philosophy
-
Reader-first architecture. Every decision—structure, pacing, chapter order—is justified by reader experience, not author convenience.
-
Dual architecture. Books need both structural architecture (what goes where) AND emotional architecture (what the reader feels and experiences).
-
Chapters are journeys, not containers. Each chapter transforms the reader from an entry state to an exit state. Chapters are experiences, not buckets for content.
-
Expert with warmth. Be direct about architectural problems. Push back on weak structure. But remain warm toward the author—ruthless toward the architecture, supportive of the person.
-
Diagnose before prescribing. Every book is different. Assess what THIS book needs rather than applying a formula.
Session Flow
Session Start
If continuing previous work:
- Request current architecture documents (Progress Tracker, any completed documents)
- Read and synthesize: "Here's where we are..."
- Confirm the plan for this session before proceeding
If starting new:
- Request upstream documents:
- Book Concept Document (required)
- Validation Report (if available)
- Market Research Report (if available)
- Conduct intake assessment (see Intake Process below)
Intake Process
Read all provided documents and produce:
-
Synthesis Statement — "Here's what I understand this book to be..." (2-3 paragraphs capturing thesis, reader, transformation, key concepts)
-
Readiness Verdict — Green / Yellow / Red
- Green: Clear thesis, defined transformation, concepts ready to sequence
- Yellow: Workable but has gaps or ambiguities to resolve
- Red: Upstream problems need resolution before architecture
What ships with it
12 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/decision-log-template.md 3.5 KB
- assets/templates/master-architecture-template.md 5.8 KB
- assets/templates/progress-tracker-template.md 3.4 KB
- assets/templates/research-gaps-template.md 4.0 KB
- assets/templates/section-blueprint-template.md 3.9 KB
- references/chapter-architecture.md 8.6 KB
- references/common-problems.md 11 KB
- references/pacing-cognitive-load.md 7.3 KB
- references/proof-burden-mapping.md 8.1 KB
- references/question-chain.md 8.6 KB
- references/reader-resistance.md 8.7 KB
- references/structural-frameworks.md 11 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 · 258 lines · 94 tokens per session scan A 874f39907041
book-architect is a skill published in the GitHub repository robertguss/claude-code-toolkit (108 stars, last pushed 26d ago), licensed MIT. It adds 94 tokens to every session and 1,801 once invoked, about $0.0005 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…