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.
git clone --depth 1 https://github.com/Fergana-Labs/stashWrote 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/fergana-labs/stash/stash)<a href="https://agentmods.dev/rules/fergana-labs/stash/stash"><img src="https://agentmods.dev/badge/rules/fergana-labs/stash/stash/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/rules/fergana-labs/stash/stash"><img src="https://agentmods.dev/badge/rules/fergana-labs/stash/stash.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 | $0.00375 | $0.00375 |
| Opus 5.5 | $0.00150 | $0.00150 |
| Sonnet 5.5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
stash 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.
What it actually says
Stash
You have the stash CLI on your PATH. Run stash --help to see commands. Use it to read transcripts, pages, and history from your Stash.
stash ls shows everything Stash can reach as one filesystem — your files, session transcripts, and every connected integration (GitHub, Slack, Gong, Gmail, Drive, Notion, …). When asked what you have access to, run it and show the tree; drill in with stash ls <source>/<path>.
Use stash vfs when you want to browse Stash like a filesystem without mounting anything into the OS. It accepts bash-shaped commands over the virtual Stash tree:
stash vfs ls /mestash vfs "find /me -maxdepth 3 -type f"stash vfs "rg \"query\" /me"stash vfs "cat '/me/README.md'"
Your activity in this repo is streamed to your Stash, so your other agents and you can see what you're working on.
When the user asks you to upload local files to Stash, use stash upload <path> --json and give the user the returned url. If you use stash upload <path> --json for a raw file upload, give the user the returned app_url.
Common reads (all support --json):
stash search "<query>"— full-text search across transcriptsstash vfs "cat '/me/sessions/_index.jsonl'"— recent eventsstash sessions agents— who's been activestash vfs "find /me -name '*.md'"— your pages
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 · 27 lines · 375 tokens per session scan A 174b60ea21c7
stash is a cursor rule published in the GitHub repository Fergana-Labs/stash (337 stars, last pushed 2d ago), licensed MIT. It adds 375 tokens to every session, about $0.0015 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 2026-08-30.
Other cursor rules, from other repositories
atomicmemory
AtomicMemory persistent memory protocol and MCP tool usage.
project-memory
This rule guides recording project events and decisions in projectmem.
demo-consume-context
Worked example that discovers, loads, and tags a context package per CONSUMING-CONTEXT-PACKAGE.md, then writes a reverse-index addendum — proves the produce/consume/tag loop end-to-end. Do NOT use for real feature work.
aictx
Cursor rule "aictx" from oldskultxo/aictx, covering aictx, priority model, default loop, inspection and advanced tools and what to record.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.