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 jovesun-lab/whetstone --skill idea-vaultgit clone --depth 1 https://github.com/jovesun-lab/whetstoneWrote 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/jovesun-lab/whetstone/idea-vault)<a href="https://agentmods.dev/skills/jovesun-lab/whetstone/idea-vault"><img src="https://agentmods.dev/badge/skills/jovesun-lab/whetstone/idea-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.
<a href="https://agentmods.dev/skills/jovesun-lab/whetstone/idea-vault"><img src="https://agentmods.dev/badge/skills/jovesun-lab/whetstone/idea-vault.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00156 | $0.01951 |
| Opus 5.5 | $0.00062 | $0.00780 |
| Sonnet 5.5 | $0.00031 | $0.00390 |
| Haiku 4.5 | $0.00016 | $0.00195 |
Grade A, and why
idea-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 23d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea Vault
A lightweight, cross-project notebook for capturing ideas the user wants to come back to — with checklists, priority, status, and optional reminders. The data lives in one plain-markdown file outside any single project, so ideas from different projects all land in the same place.
Vault location
Default data file: ~/IdeaVault/ideas.md
Default archive file: ~/IdeaVault/archive.md
On first use: check the default location. If no vault exists there, ask the user ONCE where the vault should live (accepting the default is fine), create the files from the templates below, and remember the chosen path — in your persistent memory or the user's agent config file, if your harness has one. From then on, always read and write that path. Never scatter vault files per project: one vault, every project.
Entry schema
Each idea is one block in ideas.md, separated by ---. Newest entries go on top.
## [YYYY-MM-DD] Idea title
- **Project:** {project name or "General"}
- **Status:** new | planned | in-progress | done | archived
- **Priority:** high | medium | low
- **Effort:** S | M | L
- **Tags:** #tag1 #tag2
- **Remind on:** YYYY-MM-DD _(optional)_
- **Depends on:** {idea title} _(optional)_
{one-to-three-sentence description — what, why, context}
**Checklist:**
- [ ] sub-task 1
- [ ] sub-task 2
**Source:** "{optional short quote from the conversation}"
---
YYYY-MM-DD is always today's absolute date. Resolve "today", "tomorrow", "next week"
to absolute dates before writing — a relative date in a file that outlives the
conversation is a date nobody can trust.
When to trigger
Phrase triggers (offer to save)
Treat any of these as a signal to offer capture. Never save silently — always confirm first.
- "new idea", "good idea", "I have an idea"
- "plan to do", "I want to", "I'd like to", "we should"
- "wouldn't it be cool if", "what if we", "next time"
- "save this", "remember this", "add to idea vault"
- "/idea" (explicit command)
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.
- 23d ago First seen · 249 lines · 156 tokens per session scan A e7cc4b760733
idea-vault is a skill published in the GitHub repository jovesun-lab/whetstone (8 stars, last pushed today), licensed MIT. It adds 156 tokens to every session and 1,951 once invoked, about $0.0006 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 2026-09-23.
Other skills, from other repositories
cast-org
Talk through the organization of agents and people around this work with the person, in this session: who reports to whom, what each role looks after, where their sessions go. Reads what the code and the sessions say before it trusts a plan or a task, asks what the records cannot settle, and posts each agreed change…
cast-plan
Turn a request into a plan the team can review before code exists. Explores the codebase, searches prior sessions and recorded decisions for earlier attempts, interviews the user on the open questions, then writes a codecast plan with tasks and dependencies ready for orchestrate. Use when work has several parts, when…
cast-handoff
Package the current work so the next session or a teammate can continue without reading this thread. Writes the decisions, the direction, what is verified, open questions and ordered next steps as a shared doc, pins the state, and optionally forks, spawns or hands the work to a session. Use before stopping, before a…
cast-conflicts
Before editing or fanning out work, find the live sessions on this repository that are changing the same files, show what they changed, and warn them. Use before starting a task that touches shared files, before spawning workers, or when asked who else is working on this.
cast-from-call
Turn a team call's action items into tasks people can pick up, each linked to the line in the transcript where it was agreed. Reads the call's summary and transcript, confirms each commitment against what was actually said, and files tasks marked as decided in a meeting. Use after a call, when asked what was agreed…
cast-loop
Run an autonomous loop that works through a queue of tasks one fresh session at a time, with verification as the gate and a human decision at merge. Sets up a recurring trigger that spawns a session per ready task, a precheck that spends nothing when the queue is empty, and the rules each run follows. Use for a…