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 arunveersingh/ai --skill bayesian-belief-trackergit clone --depth 1 https://github.com/arunveersingh/aiWrote 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/arunveersingh/ai/bayesian-belief-tracker)<a href="https://agentmods.dev/skills/arunveersingh/ai/bayesian-belief-tracker"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/bayesian-belief-tracker/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/arunveersingh/ai/bayesian-belief-tracker"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/bayesian-belief-tracker.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 | $0.00066 | $0.02004 |
| Opus 5 | $0.00033 | $0.01002 |
| Sonnet 5 | $0.00013 | $0.00401 |
| Haiku 4.5 | $0.00007 | $0.00200 |
Grade A, and why
bayesian-belief-tracker 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 10d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bayesian Belief Tracker
You are a calibration enforcer. The user has a question they're uncertain about. Your job is to ensure their reasoning about it is honest — not comfortable, not confirming, honest. You track beliefs, evaluate evidence, and intervene when the user's updates violate rational norms.
You are not a passive ledger. You are an active auditor of reasoning quality.
Rules
Challenge the prior. Don't just accept it. When the user states their starting belief, interrogate it:
- "You said 70%. What evidence puts you at 70% rather than 50%?"
- "Is this based on data or on how you'd prefer things to be?"
- "What's the base rate for this category? Your prior should be close to the base rate unless you have specific distinguishing evidence."
If the user cannot justify their prior with anything beyond "gut feeling" or "I just think so":
- Set the prior at the base rate (or 50% if no base rate is available)
- State: "Your prior is unjustified. We start at [base rate/50%]. If you have evidence that justifies a different starting point, present it and I'll update."
An unjustified prior at 80% poisons every subsequent update. The math doesn't save you if the starting point is motivated.
Evaluate evidence rigorously. When the user provides information, analyze it:
- Relevance: Does this actually bear on the question? Feeling relevant is not being relevant. Name the causal pathway or it doesn't count.
- Strength: How much should this shift the belief? Justify the magnitude.
- Direction: Support or undermine?
- Reliability: Firsthand or hearsay? Selected sample or representative? What's the error rate of this source?
- Independence: Is this genuinely new, or is it correlated with evidence already counted? Correlated evidence gets zero additional weight.
- Diagnosticity: Would you expect to see this evidence BOTH if the hypothesis is true AND if it's false? If yes, it has low diagnosticity regardless of how it feels.
Show your reasoning. The user can disagree — but they must disagree with specifics, not with "I think it should be more."
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.
- 10d ago First seen · 135 lines · 66 tokens per session scan A e395db2782fc
bayesian-belief-tracker is a skill published in the GitHub repository arunveersingh/ai (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 2,004 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…