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 skills/datasift-ty-personal/siftstack/sift-operationsnpx skills add DataSift-Ty-Personal/SiftStack --skill sift-operationsgit clone --depth 1 https://github.com/DataSift-Ty-Personal/SiftStackWrote 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/sift-operations)<a href="https://agentmods.dev/skills/datasift-ty-personal/siftstack/sift-operations"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/sift-operations.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 | $0.00173 | $0.03319 |
| Opus 5 | $0.00086 | $0.01659 |
| Sonnet 5 | $0.00035 | $0.00664 |
| Haiku 4.5 | $0.00017 | $0.00332 |
Grade A, and why
sift-operations 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 4d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
REI Sift Operations Encyclopedia
Complete operational knowledge base for REI Sift (DataSift.ai). Covers sequences, filter presets, niche/bulk sequential marketing, SiftLine boards, drip campaigns, events/tasks, daily operations, and troubleshooting.
When to use this skill: Any time a user asks about configuring, building, troubleshooting, or understanding workflows inside REI Sift. This includes sequence setup, preset building, board management, lead pipeline configuration, daily operational routines, team setup, and import workflows.
Execution Mode Detection
This is a routing/reference skill that directs to other skills for implementation. When Playwright automation is available (Claude Code CLI with DATASIFT_EMAIL/DATASIFT_PASSWORD set), the following companion skills provide automated execution:
| Task | Companion Skill | Automation Script |
|---|---|---|
| Filter preset management | sequential-presets.skill |
sequential-presets/scripts/manage_presets.py |
| Sequence creation | sift-sequences.skill |
sift-sequences/scripts/manage_sequences.py |
| Phone tag upload | phone-validator.skill |
phone-validator/scripts/upload_phone_tags.py |
| Market research | sift-market-research.skill |
sift-market-research/scripts/extract_market_finder.py |
Those scripts live in the companion skill, not in this plugin. Each one uses scripts/datasift_core.py for login, cookie persistence, and popup dismissal, and this plugin ships its own copy of that helper. Credentials are loaded from .env or environment variables, never hardcoded.
How to Use This Skill
When a user asks a Sift question:
- Identify the domain -- determine which area of Sift the question falls into
- Load the right reference -- read the appropriate reference file(s) for detailed configurations
- Respond in hybrid format -- give a brief concept explanation, then provide the step-by-step walkthrough
- Generate docs when useful -- for complex preset maps or sequence plans, create a markdown or Excel file the user can keep
- Fall back gracefully -- if the question doesn't match a specific category, start with general-operations.md and the Core Concepts section below
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/acquisitions-sequences.md 5.8 KB
- references/board-workflows.md 4.6 KB
- references/bulk-sequential-presets.md 4.3 KB
- references/drip-campaigns.md 5.7 KB
- references/events-and-tasks.md 7.7 KB
- references/filter-configurations.md 4.2 KB
- references/general-operations.md 13 KB
- references/lead-management-sequences.md 7.9 KB
- references/niche-sequential-presets.md 6.2 KB
- references/sequence-ideation.md 4.4 KB
- references/sequences-core.md 4.6 KB
- references/troubleshooting.md 7.8 KB
- scripts/datasift_core.py 16 KB runs code
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.
- 4d ago First seen · 250 lines · 173 tokens per session scan A eb1d6f9165bf
sift-operations is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (21 stars, last pushed today), licensed MIT. It adds 173 tokens to every session and 3,319 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…