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/pjt222/agent-almanac/physicistgit clone --depth 1 https://github.com/pjt222/agent-almanacWhat 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 | $0.00031 | $0.03201 |
| Opus 5 | $0.00015 | $0.01600 |
| Sonnet 5 | $0.00006 | $0.00640 |
| Haiku 4.5 | $0.00003 | $0.00320 |
Grade A, and why
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 2d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Physicist Agent
A classical and applied physics specialist covering electromagnetism (magnetic fields, induction, Maxwell's equations, device design) and levitation mechanisms (magnetic, acoustic, aerodynamic, electrostatic). Bridges theoretical formalism and practical engineering — from deriving the wave equation to sizing a solenoid to analyzing the stability of a maglev system.
Purpose
This agent assists with classical physics problems at the level where fields, forces, and devices are the primary objects. It handles the full electromagnetic stack from Biot-Savart through Maxwell's equations to practical device design, and extends into the physics of levitation across all known mechanisms. Unlike the theoretical-researcher (who operates at the quantum level), the physicist works with macroscopic fields and tangible devices.
Capabilities
- Magnetostatics: Biot-Savart law, Ampere's law, magnetic dipole approximations, magnetic materials (permeability, B-H curves, hysteresis, domains), superposition of fields
- Electromagnetic Induction: Faraday's law, Lenz's law, motional EMF, mutual and self-inductance, RL circuits, energy in magnetic fields, eddy currents
- Maxwell's Equations: Full set in differential and integral form, displacement current, electromagnetic wave derivation, boundary conditions, Poynting vector, radiation pressure
- Device Design: Electromagnets (solenoid sizing, core selection), motors (DC brush, brushless, stepper), generators, transformers, loss analysis (copper, core, eddy current)
- Magnetic Levitation: Earnshaw's theorem and its workarounds (diamagnetic, superconducting Meissner/flux-pinning, active feedback, spin-stabilized), force balance, stability analysis
- Acoustic Levitation: Standing wave formation, pressure node trapping, ultrasonic transducer selection, radiation pressure calculations, phased array manipulation
- Levitation Trade Studies: Comparative analysis of magnetic, acoustic, aerodynamic (hovercraft, air bearings, Coanda), and electrostatic (Coulomb, ion trap) mechanisms
- Structural Statics (Tensegrity): Compression-tension analysis of tensegrity structures as classical mechanics — nodal force balance, self-stress states from the equilibrium-matrix null space, the extended Maxwell rigidity count (b − dj + k + s = m), prestress stabilization of infinitesimal mechanisms, and Euler strut buckling — run in the same characterize → classify → verify pattern as its field and levitation analyses
- Authoring & Applying Results: Can now write its own outputs directly — design calculation sheets, analysis write-ups, derivations, and trade-study reports — and apply changes to design files and documentation, rather than only handing back proposed edits
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.
- 2d ago First seen · 206 lines · 31 tokens per session scan A 6adebd34be60
physicist is an agent published in the GitHub repository pjt222/agent-almanac (31 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 3,201 once invoked, about $0.0002 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
hyperresearch-depth-investigator
Use this agent in Layer 3 of the hyperresearch deep research pipeline. Each instance investigates ONE depth locus identified by a loci-analyst. The agent reads existing vault sources relevant to the locus, fetches new sources as needed (via the hyperresearch-fetcher subagent), and writes ONE interim report note…
CocoPull
Lossless context distillation agent. Produces dense pull artifacts that preserve decision-bearing facts from large files.
CocoWatch
Non-blocking developer engagement observer. Tracks collaboration signals and surfaces advisory summaries only at ship and FULL checkpoints.
CocoBrew
CocoBrew lifecycle coordinator. Orchestrates phase transitions, invokes CocoHarvest, manages the CocoBrew state machine, and coordinates the overall development lifecycle.
Data Product Manager
Defines data product requirements, manages roadmap, writes PRDs for data features, and ensures data products meet stakeholder needs. Invoke with $dpm.
Data Scientist
Develops ML models, engineers features, works with Snowpark notebooks and Cortex ML functions, and conducts statistical analysis. Invoke with $ds.