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/doctor)<a href="https://agentmods.dev/skills/datasift-ty-personal/siftstack/doctor"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/doctor/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/doctor"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/doctor.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 | $0.00121 | $0.00535 |
| Opus 5.5 | $0.00048 | $0.00214 |
| Sonnet 5.5 | $0.00024 | $0.00107 |
| Haiku 4.5 | $0.00012 | $0.00053 |
Grade A, and why
doctor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
SiftStack doctor
Answer one question: of the SiftStack skills, what runs today and what is blocked on what.
Run it
python "${CLAUDE_PLUGIN_ROOT}/scripts/doctor.py"
Use python3 if python is not on the PATH. Add --env-dir <folder> when the person keeps their .env somewhere other than the current folder, and --json when you need to reason over the result instead of showing it.
The script reads environment variables and a .env in the chosen folder. It records which NAMES are set and never reads a value into its output. You MUST NOT open or print the .env yourself, because the whole point of the script is that a credential never lands in the conversation.
Report it
Give the person the three groups in this order, in plain words:
- Works right now. These need nothing.
- Signed-in services. Keys are fine, but the skill drives a site they must be logged in to. This cannot be checked from here, so say so instead of calling it ready.
- Needs a credential. For each: the variable name, the real cost, and the route to use without it. A blocked skill with a fallback is not a dead end, so always say the fallback in the same breath.
Then offer the setup skill if anything is blocked and they want to unblock it. Do not push keys on someone whose work is covered by the first group.
When it cannot run
No Python available (some Cowork sessions): read ${CLAUDE_PLUGIN_ROOT}/data/requires.json directly. Each package lists requires.tier (none, account, api), requires.env, requires.cost and requires.fallback. Report tier none as working, and everything else as "needs X", since without the script you cannot see which variables are set.
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 · 33 lines · 121 tokens per session scan A 028c9b852517
doctor is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (23 stars, last pushed 23d ago), licensed MIT. It adds 121 tokens to every session and 535 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.
doctor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| doctorDataSift-Ty-Personal/SiftStack | Skill | 23 | 23d ago | MIT | A | 121 | Claude Code |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | yesterday | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| triaging-web-analytics-supportPostHog/posthog | Skill | 41k | yesterday | none | A | 151 | Claude Code, Codex |
| diagnosing-missing-recordingsPostHog/posthog | Skill | 41k | yesterday | none | A | 76 | Claude Code, Codex |