sift-presets

sift-presets is a command for coding agents from DataSift-Ty-Personal/SiftStack. It costs 5 tokens per session (411 once invoked), scanned A, original, MIT.

A guided design process for sequential marketing filter presets in Sift. These presets are saved filtering rules applied in stages to marketing data, using either a niche strategy for targeted lists or a bulk strategy for stacked data.

In plain words
What is it for?
Use it to design niche or bulk sequential presets for marketing lists, including their targeting data, channel order, ownership, tags, and call-attempt cadence.
Why use it?
It helps turn a marketing strategy into ordered filters, tags, attempt limits, channels, and team responsibilities. It asks for the campaign details needed to tailor the presets.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the sift-operations plugin — 1 skill, 3 commands shipped together

Install

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.

agentmods
npx agentmods add commands/datasift-ty-personal/siftstack/sift-presets
Clone the repo
git clone --depth 1 https://github.com/DataSift-Ty-Personal/SiftStack

Or install sift-operations, the plugin that ships this one along with the rest of its 1 skill, 3 commands.

Wrote 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.

agentmods badge for sift-presets

README.md
[![agentmods](https://agentmods.dev/badge/commands/datasift-ty-personal/siftstack/sift-presets.svg)](https://agentmods.dev/commands/datasift-ty-personal/siftstack/sift-presets)
Your own site
<a href="https://agentmods.dev/commands/datasift-ty-personal/siftstack/sift-presets"><img src="https://agentmods.dev/badge/commands/datasift-ty-personal/siftstack/sift-presets.svg" alt="Measured on agentmods" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 411 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00005 $0.00411
Opus 5 $0.00003 $0.00205
Sonnet 5 $0.00001 $0.00082
Haiku 4.5 $0.00001 $0.00041

Measured 3d ago against content hash d402987ff568, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sift-presets 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 3d 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.

plugins/sift-operations/commands/sift-presets.md · 39 lines

What it actually says

The user wants to design sequential marketing filter presets. Follow the consultative workflow:

  1. Read the skill file at ${CLAUDE_PLUGIN_ROOT}/skills/sift-operations/SKILL.md for context.

  2. Determine if they need Niche or Bulk sequential presets based on $ARGUMENTS. Read the appropriate reference:

    • For Niche: ${CLAUDE_PLUGIN_ROOT}/skills/sift-operations/references/niche-sequential-presets.md
    • For Bulk: ${CLAUDE_PLUGIN_ROOT}/skills/sift-operations/references/bulk-sequential-presets.md
    • Always also read: ${CLAUDE_PLUGIN_ROOT}/skills/sift-operations/references/filter-configurations.md
  3. Discovery — Ask the user:

    • Strategy: Niche Sequential (first-to-market) or Bulk Sequential (stacked data)?
    • Niche Lists: What specific lists are they targeting?
    • Marketing Channels: Which channels, in what order?
    • Team Structure: Who handles each part?
    • Data Tags: What tag identifies their marketing list?
    • Attempt Cadence: How many call attempts before moving to next stage?
  4. Design — Start from the base template and customize:

    • Adjust lists and tags to match their specific data
    • Modify attempt thresholds based on their cadence
    • Add or remove presets based on their marketing channels
  5. Present — Create a complete preset map document with:

    • Folder name
    • Numbered preset table with names and purposes
    • Exact filter block configurations for each preset
    • Save as a markdown file to the workspace folder
  6. Implementation Guidance — Walk them through building each preset:

    • Start with "00. Needs Skipped"
    • Build in numerical order
    • Test each preset after creation
Changes

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.

  1. 3d ago First seen · 39 lines · 5 tokens per session scan A d402987ff568

Subscribe to this mod's changes

sift-presets is a command published in the GitHub repository DataSift-Ty-Personal/SiftStack (21 stars, last pushed 6d ago), licensed MIT. It adds 5 tokens to every session and 411 once invoked, about $0.0000 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.