Borrowing it
Nothing to install: this file belongs to upstash/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/upstash/skills/main/AGENTS.mdgit clone --depth 1 https://github.com/upstash/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/instructions/upstash/skills/agents-md)<a href="https://agentmods.dev/instructions/upstash/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/upstash/skills/agents-md/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/instructions/upstash/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/upstash/skills/agents-md.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 | $0.01959 | $0.01959 |
| Opus 5.5 | $0.00784 | $0.00784 |
| Sonnet 5.5 | $0.00392 | $0.00392 |
| Haiku 4.5 | $0.00196 | $0.00196 |
Grade A, and why
skills AGENTS.md 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 22d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide
Keep skill docs short and effective
Skills are consumed by agents, not read as blog posts. Say what the correct behaviour is and show it — then stop. Don't pile on caveats, notes and inline comments beyond what a reader needs to act on the example.
Never edit skills/upstash/ by hand
It is generated by scripts/build.mjs from each skills/upstash-*/SKILL.md. The build strips the frontmatter and writes overview.md into the combined skill.
To change a sub-skill:
- Edit
skills/<skill-name>/SKILL.md— the source of truth. - Run
npm run buildto regenerateskills/upstash/. - Commit both the source and the regenerated output.
CI runs npm run check, which fails if the generated output is stale. check.mjs asserts that git status --porcelain is empty after rebuilding, so it only passes on a fully clean tree — commit your source edits and the regenerated output before running it, otherwise it reports them as "out of date".
The build's pre-check also refuses to run while skills/upstash/ has unstaged changes — if you edited it by mistake, git restore skills/upstash/ first.
MCP first, CLI second
The plugins now install the hosted MCP server alongside the skills, so for
account and data operations the agent usually has authenticated tools already
in the session — creating and inspecting databases, indexes and Blob buckets,
running Redis commands, stats, logs, backups, QStash schedules and the DLQ, plus Box
(shell, browser, git, previews) and Blob upload URLs. skills/upstash-box-remote-work/
is the one skill written for those remote Box and Blob tools. The CLI covers
the same ground but needs a global npm install, a login and an API key.
So skills/upstash-cli/ opens by telling the agent to prefer the MCP when its
tools are present and to fall back to the CLI for shell work — CI steps,
provisioning scripts, piping JSON — and scripts/header.md says the same in
the combined skill's routing preamble. Keep that ordering when editing either
one, and do not add CLI instructions to an SDK skill that would pull an agent
away from the MCP.
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.
- 22d ago Changed · +3 lines · +74 tokens per session c45d41fe5d89
- 1mo ago Changed · +2 lines · +39 tokens per session d7508cafdf3f
- 1mo ago Changed · +2 tokens per session 9161b75e2e75
- 1mo ago Changed · +103 lines · +1,335 tokens per session a7c617fdc784
- 1mo ago Changed · +8 lines · +240 tokens per session 7ee7be44dafe
- 1mo ago First seen · 20 lines · 269 tokens per session scan A 287a3a38cbb3
skills AGENTS.md is an instructions file published in the GitHub repository upstash/skills (31 stars, last pushed 12d ago), licensed MIT. It adds 1,959 tokens to every session, about $0.0078 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.