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.
npx skills add jnPiyush/AgentX --skill prompt-versioninggit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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.
[](https://agentmods.dev/skills/jnpiyush/agentx/prompt-versioning)<a href="https://agentmods.dev/skills/jnpiyush/agentx/prompt-versioning"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/prompt-versioning/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.
<a href="https://agentmods.dev/skills/jnpiyush/agentx/prompt-versioning"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/prompt-versioning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.01191 |
| Opus 5.5 | $0.00019 | $0.00476 |
| Sonnet 5.5 | $0.00009 | $0.00238 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
prompt-versioning 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Versioning
WHEN: Managing prompts as versioned production assets with diffable changes, prompt variants, few-shot evolution, evaluation baselines, promotion criteria, and rollback safety.
When to Use
- Introducing prompt files into a team workflow for the first time
- Managing prompt variants per model, task, or environment
- Reviewing prompt changes with eval evidence instead of subjective judgment only
- Promoting prompts through dev, canary, and production stages
- Rolling back bad prompt releases safely
Decision Tree
Changing a prompt?
+- Small wording tweak only?
| - Still run regression tests against the fixed dataset
+- Few-shot examples changed?
| - Treat as a semantic behavior change and compare to baseline
+- New model target?
| - Branch or parameterize prompt variants per model family
+- Multiple environments?
| - Keep one source prompt with explicit overlays or clear variant files
+- Need rollback?
| - Keep last-known-good version and accepted baseline together
-- Need reviewability?
- Store prompts as files, never hidden inside code or portal-only state
Core Rules
- Every prompt must live in a repo file, not only in code, a portal, or a secret note.
- Every meaningful prompt change requires evaluation evidence against a stable dataset or rubric.
- Prompt variants must have a naming scheme that communicates role, model target, and lifecycle stage.
- Accepted baselines belong next to prompt evolution, not in someone else's memory.
- Rollback must be trivial: the previous approved prompt and its baseline should be easy to restore.
Directory Pattern
prompts/
support-agent.md
support-agent.gpt-5.md
support-agent.claude-opus.md
templates/
evaluation/
datasets/
rubrics/
baseline.json
Versioning Pattern
- Use Git as the source of truth.
- Add a short header in each prompt with purpose, target model family, owner, and last validated date.
- When variants diverge materially, split them into separate files rather than hiding branches inside code.
- Record why a prompt changed, not only what text changed.
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.
- 1mo ago Changed 9bc0b5704b23
- 1mo ago First seen · 129 lines · 47 tokens per session scan A c2f911852239
prompt-versioning is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,191 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 2026-09-03.
Other skills, from other repositories
typesafe-ai
Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when…
prompt-versioning-hygiene
This skill should be used when the user mentions "prompt engineering", "prompt versioning", "prompt management", "system prompt", "prompt template", "manage prompts", or "prompts scattered in code". It provides a methodology for treating prompts as versioned, reviewable, testable code rather than magic strings buried…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…