Prompt Version Control Workflow

Prompt Version Control Workflow is a skill for Claude Code, Codex from Notysoty/openagentskills. It costs 30 tokens per session (1,807 once invoked), scanned A, original, MIT.

A workflow for storing and managing the instructions given to AI systems, with named versions and tracked changes.

In plain words
What is it for?
It is for organizing prompts in files or other storage, comparing revisions, running A/B tests, promoting versions between environments, and defining rollback rules.
Why use it?
It helps teams review prompt changes, test new versions before release, spot regressions, and return to an earlier version without a full code deployment.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for cline. Also seen: positional $N argument; mentions Claude Code; mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/eval-prompt-candidate.py "$prompt_name" "$CANDIDATE".

Good fit It is for organizing prompts in files or other storage, comparing revisions…

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Notysoty/openagentskills
agentmods
npx agentmods add skills/notysoty/openagentskills/prompt-version-control

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 Prompt Version Control Workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/notysoty/openagentskills/prompt-version-control.svg)](https://agentmods.dev/skills/notysoty/openagentskills/prompt-version-control)
Your own site
<a href="https://agentmods.dev/skills/notysoty/openagentskills/prompt-version-control"><img src="https://agentmods.dev/badge/skills/notysoty/openagentskills/prompt-version-control.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,807 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 $0.00030 $0.01807
Opus 5 $0.00015 $0.00903
Sonnet 5 $0.00006 $0.00361
Haiku 4.5 $0.00003 $0.00181

Measured 6d ago against content hash 119eb5b0c695, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Prompt Version Control Workflow 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 6d 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-version-control/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Version Control Workflow

What this skill does

This skill designs a prompt versioning workflow so you can track changes, test before promoting, and roll back safely. Most teams store prompts as hardcoded strings inside application code — this means prompt changes go unreviewed, regressions are invisible, and rollbacks require a full code deploy. This skill fixes that.

How to use

Claude Code / Cline

Copy this file to .agents/skills/prompt-version-control/SKILL.md in your project root.

Then ask:

  • "Use the Prompt Version Control skill to set up versioning for our prompts."
  • "How should we manage prompt versions across staging and production?"

Provide:

  • Number of prompts in your system
  • Current storage method (hardcoded, env vars, database, files)
  • Whether you need A/B testing or just safe deploys
  • Tech stack

Cursor / Codex

Describe your current prompt management alongside these instructions.

The Prompt / Instructions for the Agent

Step 1 — Choose a storage approach

Approach Best for Tradeoffs
Git files (prompts/*.md) Small teams, prompts change rarely Simple, diffable, but requires deploy to change
Database table Prompts change frequently, need hot-swap Live updates, but needs admin UI
Dedicated tools (Braintrust, LangSmith, Langfuse) Eval-heavy teams Best tooling, external dependency
Environment variables Single prompt, simple apps Easy but no history, no diffs

Recommended default: Git files — prompts are code, they should be reviewed like code.

Step 2 — File-based prompt versioning

prompts/
  support-bot/
    v1.md          ← old version (keep for rollback reference)
    v2.md          ← current production version
    v3.md          ← candidate being tested
    current.txt    ← contains "v2" — points to active version
  document-summarizer/
    v1.md
    current.txt

Each prompt file has a frontmatter header:

---
version: 2
created: 2026-01-15
author: tates
description: Improved tone, added JSON output format
changes_from_previous:
  - Added JSON output requirement
  - Shortened system role description
  - Added explicit refusal instructions
---

You are a customer support agent for Acme Corp...

Read the full file on GitHub · 239 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. 6d ago First seen · 239 lines · 30 tokens per session scan A 119eb5b0c695

Subscribe to this mod's changes

Prompt Version Control Workflow is a skill published in the GitHub repository Notysoty/openagentskills (9 stars, last pushed 23d ago), licensed MIT. It adds 30 tokens to every session and 1,807 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

llm-tester

You are the LLM Tester, specializing in systematic prompt evaluation, red-teaming, and LLM output quality assurance. You replace "vibes-based" AI evaluation with rigorous, automated, and repeatable verification suites.

buiphucminhtam/forgewright · 49 tokens

free-model-triage

Route high-volume, low-stakes triage (reading piles, inbox summaries, needs-reply flags) to a free model with a strict output schema. Use when the user wants one-line summaries of many items cheaply, asks to triage email, articles, or reports with AI, or wants to decide what's worth reading without paying premium…

Neeeophytee/ai-cost-cutter-skills · 77 tokens

ai-engineering-toolkit

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.

aboalrejal-ai/skills · 47 tokens

ai-engineering-toolkit

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.

sickn33/agentic-awesome-skills · 47 tokens

airflow-dag-patterns

Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.

wshobson/agents · 42 tokens

prompt-master

Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…

nidhinjs/prompt-master · 78 tokens