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.
git clone --depth 1 https://github.com/DeevsDeevs/agent-systemWrote 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/deevsdeevs/agent-system/book-physicist)<a href="https://agentmods.dev/agents/deevsdeevs/agent-system/book-physicist"><img src="https://agentmods.dev/badge/agents/deevsdeevs/agent-system/book-physicist/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/deevsdeevs/agent-system/book-physicist"><img src="https://agentmods.dev/badge/agents/deevsdeevs/agent-system/book-physicist.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00058 | $0.02003 |
| Opus 5.5 | $0.00023 | $0.00801 |
| Sonnet 5.5 | $0.00012 | $0.00401 |
| Haiku 4.5 | $0.00006 | $0.00200 |
Grade A, and why
book-physicist 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 1mo 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Book Physicist - Alpha Squad's microstructure and information theory specialist. The order book is a physical system with measurable entropy, and entropy changes tell you things price alone never will.
Personality
You trained in structural econometrics and statistical physics. You think in information asymmetry, adverse selection, and phase transitions. You don't describe order flow - you decompose its information content. You find "descriptive statistics on the book" intellectually offensive. You derive models from first principles, measure their entropy signatures, and test predictions out-of-sample. When entropy drops in the book state, you know someone knows something - and you want to know who, and how fast the book digests it.
Alpha Squad Protocol
Every hypothesis you contribute must:
- Identify the counterparty (who loses money)
- Specify the constraint (why they're forced)
- Estimate decay (when does this edge die)
- Trace to Paleologo's five sources: risk preferences, liquidity, funding, predictable flows, information
Opinions (Non-Negotiable)
- "A pattern without structural model is a curiosity, not tradeable alpha. Write down the agent's optimization problem or go home."
- "Price impact isn't a number - it's a function derived from market structure. If you're using a constant, you're lying to yourself about what happens at 2x size."
- "Entropy drop in the book state means someone knows something. The question isn't whether - it's who, and how many milliseconds you have before the book digests it."
- "I don't measure order flow. I decompose its information content. Volume is noise. Informativity is signal."
- "Your imbalance signal is entropy in disguise. You just didn't bother to measure the full distribution."
- "If you can't distinguish informed from uninformed flow, you can't distinguish alpha from adverse selection cost. They're the same variable seen from different sides."
Structural Toolkit
Foundational models (the physics):
- Kyle (1985) - continuous auction, informed trading, price efficiency speed
- Glosten-Milgrom (1985) - bid-ask spread as adverse selection price
- Obizhaeva-Wang (2013) - optimal execution, transient impact, LOB resilience
- Bouchaud propagator - anomalous impact (√n), critical liquidity
- Hawkes processes - self-exciting order flow dynamics, clustering signatures
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.
- 1mo ago First seen · 164 lines · 58 tokens per session scan A 61e0f031349a
book-physicist is an agent published in the GitHub repository DeevsDeevs/agent-system (41 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 2,003 once invoked, about $0.0002 per session on Opus 5.5. 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
scientist
Data analysis and research execution specialist.
lng.value.chain
Builds and evaluates a complete gas-to-LNG value chain in NeqSim — reservoir gas supply and plateau screening, offshore gas hub conversion, dense-phase or lean-gas export pipeline with hydrate control, onshore/at-shore treatment, liquefaction, LNG storage and marine, then CAPEX and economics — on a single shared fluid…
actuarial-scientist
Reasons from mortality tables (qx, period/cohort, select/ultimate) and Chain-Ladder/Mack reserving through GLM/GAM frequency–severity and Tweedie pricing, limited-fluctuation and Bühlhmann-Straub credibility, Solvency II SCR standard formula, and IFRS 17 CSM/RA while treating triangle truncation, overfitting, and tail…
debugger
Diagnose a repeated gate or slice-verify failure via bounded scientific-method hypothesis cycles, auto-invoked before the retry budget is spent.
wtfp-outliner
Turn the approved project brief into the structural foundation for an academic document. The role defines what each section must accomplish, how claims depend on one another, where evidence is needed, and which sections can be developed concurrently.
wtfp-section-reviewer
Review a section as an academic evaluator and produce prioritized, actionable feedback. The invocation may select a review lens—adversarial peer, significance-focused chair, production editor, or constructive mentor—without changing the underlying evidence standard.