llm-calibration-logprobs

llm-calibration-logprobs is a skill for Codex from scdenney/open-science-skills. It costs 151 tokens per session (4,329 once invoked), scanned A, original, no licence file.

An analysis of an LLM’s token-level probabilities, which show how confident it was while producing text. It measures whether those confidence estimates match actual correctness.

In plain words
What is it for?
Use it to calculate confidence measures such as expected calibration error and Brier scores, create reliability diagrams, and send low-confidence cases for review.
Why use it?
It helps identify decisions the model is uncertain about and reveals when its confidence is poorly calibrated.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to calculate confidence measures such as expected calibration error and Brier scores, create reliability diagrams, and send low-confidence cases for review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/scdenney/open-science-skills/llm-calibration-logprobs
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 scdenney/open-science-skills --skill llm-calibration-logprobs
Clone the repo
git clone --depth 1 https://github.com/scdenney/open-science-skills

Made for: 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 llm-calibration-logprobs

README.md
[![agentmods](https://agentmods.dev/badge/skills/scdenney/open-science-skills/llm-calibration-logprobs/github.svg)](https://agentmods.dev/skills/scdenney/open-science-skills/llm-calibration-logprobs)
Your own site
<a href="https://agentmods.dev/skills/scdenney/open-science-skills/llm-calibration-logprobs"><img src="https://agentmods.dev/badge/skills/scdenney/open-science-skills/llm-calibration-logprobs/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 llm-calibration-logprobs

Your own site · 80×15
<a href="https://agentmods.dev/skills/scdenney/open-science-skills/llm-calibration-logprobs"><img src="https://agentmods.dev/badge/skills/scdenney/open-science-skills/llm-calibration-logprobs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,329 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 unknown 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 $0.00151 $0.04329
Opus 5 $0.00076 $0.02165
Sonnet 5 $0.00030 $0.00866
Haiku 4.5 $0.00015 $0.00433

Measured 5d ago against content hash fd1573e1b07b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

llm-calibration-logprobs 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.

codex/llm-calibration-logprobs/SKILL.md · 95 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Files

What ships with it

1 file 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.

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. 5d ago Changed · +1 lines fd1573e1b07b
  2. 8d ago Changed · +110 tokens per session 91c11819f2bf
  3. 12d ago First seen · 94 lines · 41 tokens per session scan A 9507db6daf2e

Subscribe to this mod's changes

llm-calibration-logprobs is a skill published in the GitHub repository scdenney/open-science-skills (55 stars, last pushed 2d ago), with no licence file. It adds 151 tokens to every session and 4,329 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

llava

Vision-language chat: VQA, captioning, image dialogue.

NousResearch/hermes-agent · 16 tokens

claude-api

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude…

asgeirtj/system_prompts_leaks · 294 tokens

cli-eval

Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.

diegosouzapw/OmniRoute · 34 tokens

long-context

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases…

davila7/claude-code-templates · 74 tokens

guidance

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.

davila7/claude-code-templates · 38 tokens

training-llms-megatron

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA…

davila7/claude-code-templates · 82 tokens