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 agentmods add rules/lxb12123/prompt-pocket/usuallygit clone --depth 1 https://github.com/lxb12123/prompt-pocketWrote 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/rules/lxb12123/prompt-pocket/usually)<a href="https://agentmods.dev/rules/lxb12123/prompt-pocket/usually"><img src="https://agentmods.dev/badge/rules/lxb12123/prompt-pocket/usually.svg" alt="Measured on agentmods" 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 | $0.00128 | $0.01945 |
| Opus 5 | $0.00064 | $0.00972 |
| Sonnet 5 | $0.00026 | $0.00389 |
| Haiku 4.5 | $0.00013 | $0.00194 |
Grade A, and why
usually 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 5d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/usually — Prompt Pocket
Remember your most-used prompts, manage them in one place, and pick one to run. All data and frequency counting are done by a deterministic script (0 tokens); your only job is: decide the sub-action → call the script → let the user pick from a menu → run the picked prompt.
The script (run this; it prints a single JSON object — just relay it)
The deterministic core is pocket.mjs. Resolve its path once, then reuse it:
- Preferred:
~/.prompt-pocket/pocket.mjs(absolute — works on every host and from any directory, including global / plugin installs). - In this repo:
skills/usually/scripts/pocket.mjsalso works. - Bootstrap (do this if
~/.prompt-pocket/pocket.mjsis missing and you can see the repo copy):mkdir -p ~/.prompt-pocket && cp skills/usually/scripts/pocket.mjs ~/.prompt-pocket/pocket.mjs - Keep it fresh: if you can see the repo copy, refresh the runtime copy so the native
dropdown feature is present:
cp skills/usually/scripts/pocket.mjs ~/.prompt-pocket/pocket.mjs
Below, POCKET means whichever path exists — e.g. run node ~/.prompt-pocket/pocket.mjs <command>.
Store lives at ~/.prompt-pocket/store.json (user-level, shared across agents:
Claude / Codex / OpenCode read the same pocket).
scan reads Claude (~/.claude/projects), Codex (~/.codex/sessions) and OpenCode
(~/.local/share/opencode/opencode.db) session history.
First, decide which sub-action the user wants
From what the user said this turn (could be /usually, /usually add ..., or natural
language) pick one:
| User intent | Sub-action |
|---|---|
just /usually, "list my usual prompts", "what do I usually say", "列一下我常用的" |
list + pick to run (main flow, below) |
| "save this", "add this one", "remember this for later" | add |
| "delete that one", "remove …", "delete" | delete |
| "change that one", "rename … to …", "edit" | edit |
| "is there a … one", "find …", "did I say … before" | find |
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.
- 5d ago First seen · 148 lines · 128 tokens per session scan A 5f713ccb6f67
usually is a cursor rule published in the GitHub repository lxb12123/prompt-pocket (4 stars, last pushed 2mo ago), licensed MIT. It adds 128 tokens to every session and 1,945 once invoked, about $0.0006 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.
Other cursor rules, from other repositories
ai-product-canvas
Structure AI and ML product decisions with the rigour of any product decision. Use when building AI-powered features, evaluating LLM integrations, designing AI products, or assessing AI readiness. Produces a complete AI product canvas covering problem definition, model approach, data requirements, evaluation…
context-engineering-review
Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself. Use when asked to review a system prompt and context assembly, cut token usage without losing quality, debug an agent that ignores instructions, or audit how retrieval results, history, and…
prompt-library-builder
Build a personal library of reusable prompts for the things you ask AI again and again — so you stop rewriting the same request from scratch. Use when asked help me build a prompt library, save my best prompts, I keep writing the same prompts, or organize my AI prompts. Produces a captured set of your recurring AI…
ai-context-primer
Build the context an AI needs to do a task well — the background, constraints, examples, and format it can't guess — so you get a great result on the first try instead of a generic one you have to keep correcting. Use when asked why does AI give me generic answers, how do I give AI better context, my AI results are…
get-more-from-ai
Level up how you actually use AI — from basic one-shot questions to the techniques that get dramatically better results — matched to what you already do. Use when asked how do I get better at using AI, how do power users use AI, I feel like I'm using AI at 10%, or teach me to use AI better. Produces an honest read of…
prompt-debugging
Figure out why a prompt isn't working and fix it — diagnose the actual failure (ambiguity, missing context, wrong format, conflicting instructions) instead of randomly rewording. Use when asked why isn't my prompt working, the AI keeps ignoring my instructions, my prompt gives inconsistent results, or how do I fix…