prompt-vault

prompt-vault is a skill for Claude Code, Codex from OpenCoven/coven. It costs 39 tokens per session (454 once invoked), scanned A, original, MIT.

A local library for saving, finding, tagging, versioning, and moving reusable AI prompts. It is controlled through the `pv` command-line tool and stores data in a local SQLite database.

In plain words
What is it for?
Use it to save prompts you want to reuse, search them by words, filter them by tags, or export and import the prompt collection as JSON.
Why use it?
It removes the need to keep useful prompts in scattered notes or recreate them from memory.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to save prompts you want to reuse, search them by words, filter them by tags, or export and import the prompt collection as JSON.

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

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-vault

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/opencoven/coven/prompt-vault"><img src="https://agentmods.dev/badge/skills/opencoven/coven/prompt-vault.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 454 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 $0.00039 $0.00454
Opus 5 $0.00019 $0.00227
Sonnet 5 $0.00008 $0.00091
Haiku 4.5 $0.00004 $0.00045

Measured 10d ago against content hash 2f3dd4c443d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prompt-vault 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 10d 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-vault/SKILL.md · 64 lines

What it actually says

Prompt Vault

Local-first prompt manager. Use when asked to save a prompt, find a saved prompt, list prompts by tag, or export/import the prompt library.

Prerequisites

  • pv CLI installed: npm install -g BunsDev/prompt-vault
  • Data stored at ~/.prompt-vault.db (SQLite)

Commands

Save a prompt

pv add "prompt text here" --tags tag1,tag2
  • Tags are comma-separated, no spaces
  • Returns the prompt ID

Search prompts

pv search "keyword"
  • Substring match on prompt text

List prompts

pv list              # all prompts, newest first
pv list --tag code   # filter by tag

Export library

pv export            # JSON to stdout
pv export > prompts.json

Workflow Patterns

Save a prompt the user liked

When the user says "save that prompt" or "remember this prompt":

  1. Identify the prompt text from conversation context
  2. Ask for tags if not obvious (or infer from context)
  3. pv add "<text>" --tags <tags>

Find a prompt for reuse

When the user says "find my prompt about X" or "use that refactor prompt":

  1. pv search "X" to find matches
  2. Present the best match
  3. Use it in the current task

Suggest tags

Common useful tags: system-prompt, code-review, refactor, summary, debug, explain, test, docs, creative, agent, tool-use

Notes

  • Prompt text with quotes: escape inner quotes or use single quotes around the CLI arg
  • The DB is local-only — no sync. Use pv export to back up.
  • Search is basic substring matching (LIKE %query%)
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. 10d ago First seen · 64 lines · 39 tokens per session scan A 2f3dd4c443d5

Subscribe to this mod's changes

prompt-vault is a skill published in the GitHub repository OpenCoven/coven (47 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 454 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 2026-08-30.