decision-gates

decision-gates is a skill for Claude Code, Codex from uchicago-dsi/ai-sci-skills. It costs 59 tokens per session (861 once invoked), scanned A, original, MIT.

A framework for defining and reporting scientific decision rules. It distinguishes a mechanical check, such as a known-bad input rejection, from a scientific gate that decides whether an experiment continues, is promoted, or is stopped.

In plain words
What is it for?
Use it when proposing, approving, freezing, interpreting, or reporting promotion, continuation, stopping, or retirement criteria for a scientific run.
Why use it?
Unapproved or changing thresholds can alter the meaning of an experiment after the fact. This framework requires the metric, threshold, comparison, timing, and resulting actions to be agreed and preserved.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when proposing, approving, freezing, interpreting, or reporting promotion, continuation, stopping, or retirement criteria for a scientific run.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/uchicago-dsi/ai-sci-skills/decision-gates
Install

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.

Any agent
npx skills add uchicago-dsi/ai-sci-skills --skill decision-gates
Clone the repo
git clone --depth 1 https://github.com/uchicago-dsi/ai-sci-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for decision-gates

README.md
[![agentmods](https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/decision-gates/github.svg)](https://agentmods.dev/skills/uchicago-dsi/ai-sci-skills/decision-gates)
Your own site
<a href="https://agentmods.dev/skills/uchicago-dsi/ai-sci-skills/decision-gates"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/decision-gates/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.

agentmods 80×15 button for decision-gates

Your own site · 80×15
<a href="https://agentmods.dev/skills/uchicago-dsi/ai-sci-skills/decision-gates"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/decision-gates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 861 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00861
Opus 5.5 $0.00024 $0.00344
Sonnet 5.5 $0.00012 $0.00172
Haiku 4.5 $0.00006 $0.00086

Measured 1mo ago against content hash 2ef3aae2b2b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

decision-gates 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.

skills/decision-gates/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decision Gates

Get Explicit Approval For A Scientific Gate

Before adopting any scientific promotion, continuation, stopping, or retirement gate, present the exact:

  • metric definitions and thresholds;
  • comparison reference;
  • independent denominator;
  • aggregation;
  • evaluation timing;
  • the action triggered by pass and by fail;

and obtain explicit approval. Do not infer approval from a general experiment request, from prior autonomy, from a pilot, or from a similar gate used elsewhere.

Once approved and frozen for a run, preserve that gate and report it exactly. Any later interpretation or replacement is a separately versioned decision layer, not a retroactive edit.

A Mechanical Check Is Not A Gate

The acceptance criteria of a mechanical or developer check need no approval: a smoke that must reach a real kernel, a schema that must validate, a guardrail that must reject a known-bad input, a threshold below which a run is obviously not learning. Set those yourself and report the number.

If a criterion starts deciding whether something is promoted, retired, or continued, it has become a scientific gate and the approval rule applies again.

Check That The Gate Can Be Satisfied Before You Build For It

  • Before building review, calibration, or reducer infrastructure, enumerate the maximum independent eligible cohort under the frozen source, split, availability, and contract rules, and prove it can satisfy every predeclared denominator gate. If any gate is mathematically unreachable, stop with typed feasibility evidence instead of building the downstream workflow.
  • Before defining an identifiability or posterior-width gate, write the forward model with all fitted nuisance parameters and enumerate scale, shift, and permutation symmetries. Do not interpret a coordinate that a nuisance reparameterization leaves invariant.
  • Before setting an automated QC coverage gate, compute the manual/reference ceiling under the same policy. If the reference itself can fail, report overall coverage against that ceiling and define any fixed pass fraction on the reference-eligible subset.

Read the full file on GitHub · 89 lines

Changes

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.

  1. 1mo ago First seen · 89 lines · 59 tokens per session scan A 2ef3aae2b2b8

Subscribe to this mod's changes

decision-gates is a skill published in the GitHub repository uchicago-dsi/ai-sci-skills (20 stars, last pushed 4d ago), licensed MIT. It adds 59 tokens to every session and 861 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 2026-09-22.

Related

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…

anthropics/knowledge-work-plugins · 123 tokens

matlab

Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 44 tokens

exploratory-data-analysis

Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports 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…

K-Dense-AI/scientific-agent-skills · 83 tokens

phylogenetics

Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…

K-Dense-AI/scientific-agent-skills · 71 tokens

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.

davila7/claude-code-templates · 43 tokens

presenting-conference-talks

Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.

Orchestra-Research/AI-Research-SKILLs · 53 tokens