prompt-tuning

prompt-tuning is a skill for Claude Code from jjanczur/tyran. It costs 58 tokens per session (1,223 once invoked), scanned A, original, Apache-2.0.

A method for improving prompts and other inputs whose results vary between runs. It uses repeated measurements to separate real improvements from normal output fluctuation.

In plain words
What is it for?
Use it when comparing prompt versions, measuring model-generated output, checking conversion factors between formats, or adding tests after generation.
Why use it?
It prevents teams from changing prompts based on random variation or untested assumptions about output length and other results.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the tyran plugin — 15 skills, 5 agents, 5 hooks shipped together

Good fit Use it when comparing prompt versions, measuring model-generated output, checking conversion factors between formats, or adding tests after generation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jjanczur/tyran/prompt-tuning
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 jjanczur/tyran --skill prompt-tuning
Clone the repo
git clone --depth 1 https://github.com/jjanczur/tyran

Made for: Claude Code.

Or install tyran, the plugin that ships this one along with the rest of its 15 skills, 5 agents, 5 hooks.

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 prompt-tuning

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jjanczur/tyran/prompt-tuning"><img src="https://agentmods.dev/badge/skills/jjanczur/tyran/prompt-tuning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,223 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00058 $0.01223
Opus 5 $0.00029 $0.00611
Sonnet 5 $0.00012 $0.00245
Haiku 4.5 $0.00006 $0.00122

Measured 12d ago against content hash 11e17bcf9632, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

prompt-tuning 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 12d 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/prompt-tuning/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt tuning — working with non-deterministic output

Every rule here has a measured cost behind it. The first one alone accounts for three tuning rounds spent moving a number that had never moved.

Measure before you change anything

1. Take a noise baseline BEFORE the first edit. Same prompt, same inputs, at least two runs; record the spread of every metric you care about. A delta smaller than the spread is noise, not the effect of your change. To compare two versions, run each at least three times per input and compare medians.

Measured: ±20% output length and a jumping paragraph count with no change to the prompt at all. Three rounds of tuning were spent chasing that before anyone ran the same prompt twice.

2. Measure conversion factors between representations; never assume them. One initiative assumed a 1.15× expansion between two languages and measured 1.3–1.4×. The assumption would have invalidated the entire budget built on it. When a factor's spread is wider than your target band, no source-side budget can guarantee the target — catch the tail with a gate after the transformation instead of tightening the budget before it.

3. After three failed rewordings of the same defect on the same case, name it a KNOWN LIMITATION and hand it to a human. A fourth blind iteration is chasing noise with extra steps.

Writing the prompt

4. Every numeric example becomes a quota; every template phrase becomes a verbatim anchor. Describe the CRITERION, not the illustration. "Two threads means two paragraphs" produced two-paragraph output in six samples out of six, where an example of a two-paragraph answer had not. State criteria in both directions — a one-sided formulation works only in the direction you named.

5. A rule in a prompt is a request. Enforcement is a mechanism that runs AFTER generation — a gate plus regeneration with a targeted nudge. Confirmed on four separate properties: length ceiling, presence of figures, language of a recommendation, and post-translation condensation.

Read the full file on GitHub · 103 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. 12d ago First seen · 103 lines · 58 tokens per session scan A 11e17bcf9632

Subscribe to this mod's changes

prompt-tuning is a skill published in the GitHub repository jjanczur/tyran (79 stars, last pushed 9d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,223 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 2026-08-30.

Related

Other skills, from other repositories

prompt-best-practices

The single source of truth for prompt-engineering best practices used by this suite. Provides a named, severity-graded rubric for reviewing prompts and a set of guidelines for authoring new ones, including where prompts belong in layered/clean architectures. Read this whenever auditing, authoring, or fixing an LLM…

assist-software/claude-code-repository · 69 tokens

llm-friendly-context

Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.

shinpr/codex-workflows · 52 tokens

context-engineering

Optimize Claude Code context-window usage for accuracy and cost. TRIGGER when: hitting context limits, structuring prompts for an agent, or trimming what gets injected into a task. SKIP: persisting knowledge across sessions (use agent-memory); semantic recall tuning (use semantic-memory-mcp).

komluk/scaffolding · 62 tokens

engineer-prompts

Builds or audits testable prompt contracts with explicit outcomes, permissions, tools, evidence, and stop conditions. Use when writing reusable agent prompts, system prompts, or prompts with unclear success criteria.

Drizzy07x/Skillquiver · 44 tokens

pipeline

This skill should be used when the user asks to "create a pipeline spec", "document data transformations", "document data flow", "specify pipeline invariants", "wyx pipeline", or wants to design, retrofit, or discover data pipelines with quality invariants and boundary ownership. Produces PIPELINE.md specs.

jlifyio/wyx · 66 tokens

kanso-prompting

Use when rewriting, sharpening, or producing a prompt for Claude or another current frontier model. Sets standing rules for getting better LLM output through better prompts. Loaded by /kanso-task; not directly invoked by the user.

blakecyze/kanso · 51 tokens