agentmods.dev

calibrator

calibrator is a skill for Claude Code, Codex from TimurUgulava/claude-skills. It costs 213 tokens per session (2,755 once invoked), scanned A, original, no licence file.

A tool for improving prompts, assistants, and skills by comparing an AI-produced version with a final version edited by a person. A prompt is an instruction given to an AI system.

In plain words
What is it for?
Use it to refine instructions in files, record changes in a CHANGELOG, or produce suggested edits directly in chat.
Why use it?
It identifies recurring differences and turns them into specific instruction changes.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

not rated 14repo 16d ago A scan 213 tokens no licence

Good fit Use it to refine instructions in files, record changes in a CHANGELOG, or produce suggested edits directly in chat.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/timurugulava/claude-skills/calibrator
View source ↗ TimurUgulava/claude-skills
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 TimurUgulava/claude-skills --skill calibrator
Clone the repo
git clone --depth 1 https://github.com/TimurUgulava/claude-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 calibrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/timurugulava/claude-skills/calibrator/github.svg)](https://agentmods.dev/skills/timurugulava/claude-skills/calibrator)
Your own site
<a href="https://agentmods.dev/skills/timurugulava/claude-skills/calibrator"><img src="https://agentmods.dev/badge/skills/timurugulava/claude-skills/calibrator/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 calibrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/timurugulava/claude-skills/calibrator"><img src="https://agentmods.dev/badge/skills/timurugulava/claude-skills/calibrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 213 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,755 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 $0.00213 $0.02755
Opus 5.5 $0.00085 $0.01102
Sonnet 5.5 $0.00043 $0.00551
Haiku 4.5 $0.00021 $0.00276

Measured 2mo ago against content hash 363c583bb8ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

calibrator 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 2mo 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.

calibrator/SKILL.md · 195 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

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. 2mo ago First seen · 195 lines · 213 tokens per session scan A 363c583bb8ab

Subscribe to this mod's changes

calibrator is a skill published in the GitHub repository TimurUgulava/claude-skills (14 stars, last pushed 16d ago), with no licence file. It adds 213 tokens to every session and 2,755 once invoked, about $0.0009 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.

Building agentsData and AIPrompting
Related

calibrator compared with skills from other repositories

calibrator next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
calibratorTimurUgulava/claude-skillsSkill1416d agononeA213Claude Code, Codex
llm-app-patternsdavila7/claude-code-templatesSkill33ktodayMITA54Claude Code, Codex
prompt-engineerJeffallan/claude-skillsSkill12k7d agoMITA93Claude Code
prompt-optimizationlangwatch/langwatchSkill5.0ktodayApache-2.0A105Claude Code, Codex
omh-model-optimizationrlaope/oh-my-hermesSkill5.2ktodayMITA84Claude Code, Codex
ideogram4digitalsamba/claude-code-video-toolkitSkill2.5ktodayMITA99Claude Code
prompt-library-for-startupsaws/agent-toolkit-for-awsSkill3.4ktodayApache-2.0A228Claude Code