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 jqaisystems/jqai-ai-skills --skill idea-inboxgit clone --depth 1 https://github.com/jqaisystems/jqai-ai-skillsWrote 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/jqaisystems/jqai-ai-skills/idea-inbox)<a href="https://agentmods.dev/skills/jqaisystems/jqai-ai-skills/idea-inbox"><img src="https://agentmods.dev/badge/skills/jqaisystems/jqai-ai-skills/idea-inbox/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/jqaisystems/jqai-ai-skills/idea-inbox"><img src="https://agentmods.dev/badge/skills/jqaisystems/jqai-ai-skills/idea-inbox.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 | $0.00073 | $0.00635 |
| Opus 5.5 | $0.00029 | $0.00254 |
| Sonnet 5.5 | $0.00015 | $0.00127 |
| Haiku 4.5 | $0.00007 | $0.00064 |
Grade A, and why
idea-inbox 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea Inbox
Capture ideas at the speed they arrive and still find them later. One idea per file, dated and tagged, in a dedicated folder with an index. Dump fast, refine later.
Step 0: Locate the ideas folder (once)
- Look for an
IDEAS_INDEX.mdanywhere in the project; its folder is the ideas folder. - Otherwise look for a folder named
ideas/,Ideas/, or similar. - Otherwise ask the user where ideas should live, create the folder, and create an
IDEAS_INDEX.mdin it.
Never save idea files to the project root. A pile of loose dated files in the root is how ideas get deleted in the next cleanup.
Step 1: Capture
- Get today's date from the current-date context (format
YYYY-MM-DD). - Distill a 3 to 5 word kebab-case slug from the idea, e.g.
etsy-pinterest-autonomous-pins. - Clean up the raw input: remove filler words and false starts, keep every substantive detail. Tighten, do not summarise. If the user wrote three rough sentences, the file should contain three clean sentences, not one.
- Pick 1 to 3 tags from the index categories (see Step 2), plus
idea.
Create <ideas-folder>/<date>-<slug>.md:
---
tags: [idea, <category-tag>]
date: <date>
---
# <Idea title in plain words>
<cleaned idea text>
Step 2: Update the index
IDEAS_INDEX.md keeps one line per idea under a category heading. Default categories (create on first use, let the user rename them):
# Ideas Index
## Business
## Automation & Tools
## Design & Creative
## Client Work
## Misc
Add the new idea under the best-fitting category:
- [<Idea title>](<date>-<slug>.md) <date>: one-line hook
If an idea clearly fits a category that does not exist yet, add the category rather than forcing it into Misc.
Step 3: Confirm
Report the file path, the category it was filed under, and the one-line hook used in the index.
Rules
- One idea per file. If the user dumps three ideas in one message, create three files and say so.
- Never edit or delete existing idea files. The inbox only grows; pruning is the user's call.
- Preserve the user's meaning exactly. Cleaning filler is fine, replacing their thinking is not.
- Keep the index sorted newest first within each category.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 70 lines · 73 tokens per session scan A dad47f6fb48e
idea-inbox is a skill published in the GitHub repository jqaisystems/jqai-ai-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 73 tokens to every session and 635 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
baoyu-wechat-summary
Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory…
wordpress-editing-safety
Safety rules for editing a WordPress site through Respira. Use whenever the user mentions WordPress, Respira, editing a page or a site, a page builder, a snapshot, a duplicate, an approval, or rolling back. Covers read before write, duplicates on live pages, verifying every write, reading state before a retry…
respira-workflow
Sets the posture for working on a WordPress site through Respira: report what changed on the site, stay visible during long operations, be honest about limits, and send what Respira cannot do to the founder. Use whenever Respira is mentioned, the user references their WordPress site, or the user wants to edit a site.
kelly-email
Busabase AirApp-first email inbox-zero operator for reviewing unread mail, drafting replies, approving archive/mark-read/send actions, and executing only explicitly approved mailbox changes across configured accounts. Use when the user invokes $kelly-email, asks to process unread email, configure an email account…
kelly-messenger
Unified chat inbox (Busabase App-in-Skill) aggregating WhatsApp, Discord, Slack, and Telegram messages into one place with a reply queue. Use when the user invokes $kelly-messenger or /kelly-messenger, wants a unified inbox, chat aggregation, to read WhatsApp/Discord/Slack/Telegram messages in one place, review…
macos-app-multi-instances
Run several simultaneous instances of one macOS app (e.g. two or three accounts logged into WeChat at once) by duplicating and re-signing its .app bundle. Use when an app refuses to open a second window and just refocuses the running one, when open -n -a launches no new process, or when a second independent login…