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/dr-aneeshjoseph/prism/claudenpx skills add Dr-AneeshJoseph/Prism --skill claudegit clone --depth 1 https://github.com/Dr-AneeshJoseph/PrismWrote 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/dr-aneeshjoseph/prism/claude)<a href="https://agentmods.dev/skills/dr-aneeshjoseph/prism/claude"><img src="https://agentmods.dev/badge/skills/dr-aneeshjoseph/prism/claude.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 | $0.00000 | $0.02679 |
| Opus 5 | $0.00000 | $0.01340 |
| Sonnet 5 | $0.00000 | $0.00536 |
| Haiku 4.5 | $0.00000 | $0.00268 |
Grade A, and why
Claude 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 — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRISM v2.2 - Protocol for Rigorous Investigation of Scientific Mechanisms
Author: Dr. Aneesh Joseph
Implementation: Claude (Anthropic)
Version: 2.2 | December 2025
When to Use This Skill
Use PRISM when the user asks to:
- Evaluate scientific hypotheses quantitatively
- Compare multiple hypotheses using Bayesian methods
- Perform rigorous evidence synthesis with meta-analysis
- Calculate posterior probabilities from heterogeneous evidence
- Research and prioritize scientific questions
- Assess treatment options, drug efficacy, or technology predictions
Trigger phrases:
- "Find the best hypothesis for..."
- "Compare these hypotheses..."
- "What's the probability that..."
- "Analyze the evidence for..."
- "Which treatment is most likely to work..."
Core Philosophy
Traditional hypothesis testing asks: "Is this result statistically significant?"
PRISM asks: "Given all available evidence, what is the probability this hypothesis is true?"
This shift from binary significance to continuous credence enables:
- Comparison across different evidence types
- Principled evidence accumulation
- Explicit uncertainty quantification
- Optimizer's curse correction for multiple comparisons
Mathematical Framework
Bayesian Foundation
PRISM uses Bayes' theorem with log-odds for numerical stability:
log-odds(H|E) = log-odds(H) + log(LR)
Reference Class Priors
Instead of arbitrary priors, PRISM uses empirical base rates with Beta distributions:
phase2_clinical: 15.3% [9.0%, 23.0%] (based on FDA 2000-2020)phase3_clinical: 35.1% [26.2%, 44.7%]replication: 40.1% [30.8%, 49.8%] (based on OSF 2015)general: 50.0% (uninformative)
Hierarchical Correlation Correction
Critical: Naive multiplication of likelihood ratios causes exponential overconfidence.
PRISM uses hierarchical correlation:
- Within-cluster ρ = 0.6 (same lab/method)
- Between-cluster ρ = 0.2 (independent labs)
Effective N = Σ(cluster_size / DEFF_within) / √DEFF_between
What ships with it
3 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.
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 · 386 lines · 0 tokens per session scan A 513ba7df3af2
Claude is a skill published in the GitHub repository Dr-AneeshJoseph/Prism (7 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,679 tokens. 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 2026-08-31.
Other skills, from other repositories
golden-jupyter
Use when testing the goldenjupyter golden build.
research-collaborator
Use this skill whenever a researcher wants to test, validate, stress-test, or falsify a research idea or hypothesis — especially in AI/ML/deep learning. Trigger on phrases like "I have an idea," "would this work," "test this hypothesis," "sanity check my idea," "what's wrong with this idea," "review my results," "is…
octane
Generate hard-SF-inflected, technically dense, multi-format documents that blend cutting-edge science with literary experimentation — DFW footnotes meet Gene Wolfe unreliability meet transformer mathematics meet SMILES notation meet Gadamer's hermeneutics. Draws technical vocabulary from ML, physics/chemistry…
mathesis
Mathematical thinking as a craft and generative discipline, not computation or proof-checking. Deploy when a mathematical object or question is present and the user wants to understand rather than merely solve. Use for: seeing into a theorem rather than verifying it; choosing the right definition before the proof…
paper-algorithm-jazz
Improvisational engagement with mathematical and formal content of scientific papers. Riff on equations, interpret algorithms, explore parameter spaces.
paper-hermeneutics
Deep, multi-layered analysis of scientific papers and technical documents. Stratified readings from plain-language summary through technical breakdown to critical synthesis.