Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add DataSift-Ty-Personal/SiftStack/plugin install siftstack-coreWrote 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/datasift-ty-personal/siftstack/setup)<a href="https://agentmods.dev/skills/datasift-ty-personal/siftstack/setup"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/setup/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/datasift-ty-personal/siftstack/setup"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/setup.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 | $0.00114 | $0.00661 |
| Opus 5.5 | $0.00046 | $0.00264 |
| Sonnet 5.5 | $0.00023 | $0.00132 |
| Haiku 4.5 | $0.00011 | $0.00066 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SiftStack setup
Get someone from "installed" to "working" without making them buy anything they do not need.
1. See where they stand
Run the doctor first (python "${CLAUDE_PLUGIN_ROOT}/scripts/doctor.py" --json). Never start by listing keys.
2. Ask what they do, then pick keys for that
Ask what they want to get done this week. Map the answer to skills, and only then to keys. About half the library needs nothing at all, so many people are already done.
Every key is optional and every skill degrades instead of failing. Say the cost and the free route for each key before they decide:
- The cost and fallback for every package are in
${CLAUDE_PLUGIN_ROOT}/data/requires.json. - Where to get each key, in one line each, is in the comments of
${CLAUDE_PLUGIN_ROOT}/data/env.skills.example.
3. Create the .env
Skills read environment variables, plus a .env in the folder Claude is working in.
- If there is no
.envin the working folder, copy${CLAUDE_PLUGIN_ROOT}/data/env.skills.exampleto.envthere. - You MUST NOT overwrite an existing
.env, because it may hold keys that exist nowhere else. Append only the missing variable names, empty. - You MUST NOT ask the person to paste a key into the chat, and MUST NOT write a key value yourself, because anything typed here stays in the conversation history. Tell them which line to fill in and let them edit the file in their own editor.
- If the folder is a git repository, check that
.envis ignored before they fill it in. If it is not, add it to.gitignorefirst.
People who use many folders can set the variables at the user level in their OS instead. Both work.
4. Turn on updates (Claude Code, one time)
Third-party marketplaces do not auto-update by default. Have them run /plugin, open Marketplaces, select siftstack, and choose Enable auto-update. Without it they stay on the version they installed until they run /plugin marketplace update siftstack by hand.
In Cowork, the Plugins page has an Update button on the marketplace.
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 · 45 lines · 114 tokens per session scan A bb60d5003bf8
setup is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (23 stars, last pushed 23d ago), licensed MIT. It adds 114 tokens to every session and 661 once invoked, about $0.0005 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 2026-09-22.
setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setupDataSift-Ty-Personal/SiftStack | Skill | 23 | 23d ago | MIT | A | 114 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |