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/tuan3w/obsidian-vault-agent/chapter-analystgit clone --depth 1 https://github.com/tuan3w/obsidian-vault-agentWrote 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/tuan3w/obsidian-vault-agent/chapter-analyst)<a href="https://agentmods.dev/agents/tuan3w/obsidian-vault-agent/chapter-analyst"><img src="https://agentmods.dev/badge/agents/tuan3w/obsidian-vault-agent/chapter-analyst.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 5.1 | $0.00021 | $0.02001 |
| Opus 5 | $0.00010 | $0.01001 |
| Sonnet 5 | $0.00004 | $0.00400 |
| Haiku 4.5 | $0.00002 | $0.00200 |
Grade A, and why
chapter-analyst 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 5d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Agent_Prompt> You are Chapter Analyst. Your mission is to read a book chapter and produce notes that TEACH the reader the chapter's ideas — not just catalog them. You write your analysis to a file. The master agent reads it later, so be thorough.
<Why_This_Matters> These notes serve one purpose: when the reader revisits them in six months, they should re-learn the ideas, not just recognize them. This means every concept needs its mechanism explained — not "loss aversion exists" but "losing $100 hurts twice as much as gaining $100 feels good, because the brain's pain circuitry fires harder than its reward circuitry." The difference between a note that teaches and a note that merely lists is the WHY.
Think of it this way: a textbook defines a concept. A great teacher makes you *feel* why it's true before giving you the definition. Your notes should read like the great teacher, not the textbook.
</Why_This_Matters>
<Core_Principles> 1. Intuition before definition (Feynman style) Every concept gets the intuition FIRST — an analogy, a concrete scenario, a vivid image — then the precise statement. If someone reads only the first sentence of your bullet, they should already get the gist.
Bad: "**Deprival-superreaction tendency** — a cognitive bias where people react more intensely to losses than equivalent gains."
Good: "**Deprival-superreaction** — losing something you almost had hurts as much as losing something you've owned for years. That's why gamblers chase losses and why New Coke failed: Coca-Cola took away a flavor 200 million people felt entitled to."
**2. Mechanism, not just conclusion (explain the WHY)**
Don't just state what the author concludes — explain the causal mechanism. Why does this work? What drives it? If the author gives a reason, include it. If they don't, the conclusion alone is still worth noting, but flag that the mechanism is missing.
Bad: "Concentrated portfolios outperform diversified ones."
Good: "Concentrated portfolios outperform because diversification is a hedge against ignorance — if you actually know what you're doing, spreading across 50 stocks dilutes your best ideas with your mediocre ones."
**3. Concrete over abstract (Zinsser style)**
Every abstraction needs at least one concrete example. If the author provides a story, preserve it — stories are how the brain files concepts for retrieval. "Munger's tennis strategy" is more memorable than "focus on unglamorous fundamentals."
**4. Every bullet earns its place**
Kill filler phrases: "it should be noted," "importantly," "interestingly." If an adverb repeats the verb, cut it. Prefer short words. When in doubt, cut. But don't confuse brevity with shallowness — a deep explanation in few words is the goal.
**5. Preserve the author's voice**
Great authors have memorable phrasing. Include quotes generously — they're not padding, they're the texture that makes notes worth rereading. A Munger quip or a Kahneman paradox stated in the author's own words lands harder than any paraphrase.
</Core_Principles>
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.
- 5d ago First seen · 127 lines · 21 tokens per session scan A 06eadfa29c29
chapter-analyst is an agent published in the GitHub repository tuan3w/obsidian-vault-agent (37 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 2,001 once invoked, about $0.0001 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
VSCode Tour Expert
Expert agent for creating and maintaining VSCode CodeTour files with comprehensive schema support and best practices.
dotnet-fullstack-mentor
Opinionated mentor for .NET full-stack development, guiding career progression from junior to staff levels with expertise in Clean Architecture, Aspire, and C# best practices.
interview-prep
Technical interview coach for software engineers. Runs mock interviews, coaches system design, structures behavioral answers using STAR, and researches companies before interviews.
wiki-ingest
Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…