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 skills add winstonkoh87/Athena-Public --skill social-physics-filtergit clone --depth 1 https://github.com/winstonkoh87/Athena-PublicWrote 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/winstonkoh87/athena-public/social-physics-filter)<a href="https://agentmods.dev/skills/winstonkoh87/athena-public/social-physics-filter"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/social-physics-filter/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/skills/winstonkoh87/athena-public/social-physics-filter"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/social-physics-filter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.02634 |
| Opus 5.5 | $0.00014 | $0.01054 |
| Sonnet 5.5 | $0.00007 | $0.00527 |
| Haiku 4.5 | $0.00003 | $0.00263 |
Grade A, and why
social-physics-filter 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Physics Filter — Boundary Enforcement & Relational Diagnostics
Compiled: 2026-05-11 (retroactive synthesis of 42+ protocols) Problem Class: All interpersonal dynamics — friendships, romantic relationships, client boundaries, family patterns, social contracts, and the psychological schemas that distort rational decision-making. Axiom: "The nervous system replays what is FAMILIAR, not what is HEALTHY. Unexamined wounds select for partners/clients/deals that re-inflict the wound."
When to Use
Invoke whenever the user mentions:
- Relationship frustration, boundary violations, or interpersonal conflict
- Feelings of rejection, loneliness, validation-seeking, or people-pleasing
- Analysis of someone's behavior or motives
- Dating/relationship dynamics
- Schema therapy, IFS, or parts work
- "Am I overreacting?" / "Is this normal?" / "What should I do about [person]?"
Solution Architecture
Module 1: The Wound-Selection Diagnostic (MP-8)
The Core Loop:
Unexamined wound/schema → pattern-matching bias
→ Selects for FAMILIAR, not HEALTHY
→ Familiar option re-inflicts the wound
→ Pain reinforces the schema
→ Selection bias deepens → Loop continues
The One Question: "Is this FAMILIAR or is this HEALTHY?"
If the attraction/comfort is based on familiarity with a painful pattern, the wound is selecting.
Module 2: The Pryce Protocol (6-Point Meta-Awareness Diagnostic)
Before ANY high-stakes social action:
| Gate | Check | Red Flag |
|---|---|---|
| 1. Emotional Temperature | "Am I in a regulated state?" | Flooded/activated = delay 24 hrs |
| 2. Projection Check | "Am I seeing THEM or my schema?" | If it feels like a past wound, it IS the schema |
| 3. Audience Check | "Who am I performing for?" | If an invisible audience exists, pause |
| 4. Exit Test | "Can I walk away clean?" | If not, you're hostage |
| 5. STFU Clause | "Will saying this improve the structural outcome?" | If no strategic gain, STFU |
| 6. Blast Radius Audit | "Who else gets hurt?" | Collateral damage > 2 people = full stop |
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 · 177 lines · 34 tokens per session scan A 14c59458e5eb
social-physics-filter is a skill published in the GitHub repository winstonkoh87/Athena-Public (619 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 2,634 once invoked, about $0.0001 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 skills, from other repositories
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
cnsplots
Create, revise, and troubleshoot publication-ready scientific plots in Python with cnsplots, including distribution, regression, heatmap, genomics, survival, set, flow, and multi-panel figures. Use when a user asks for cnsplots code, Cell/Nature/Science-style visualization, precise physical figure dimensions…
cirq
Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for…
qiskit
IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware use cirq; for gradient-based quantum ML use…
explain
Deep research into a topic or issue — investigates until confident, then presents an executive summary and root-cause analysis. Use when you need to understand WHY something happens. Takes [topic, question, or issue description].
persistent_straggler
Find ranks that are slow on many steps (worstfraction), not just once.