sift-sequence

A guided setup for building a Sift sequence, which is an automated chain of triggers, conditions, and actions. It uses the relevant instructions for lead management, acquisitions, board workflows, drip campaigns, or idea generation.

In plain words
What is it for?
Use it to design Sift sequences for managing leads, acquisitions, board workflows, drip campaigns, or other operational processes.
Why use it?
It helps turn a broad automation idea into a clearly defined sequence. If the request is vague, it identifies the missing details by asking what starts the sequence, what it filters, what it does, and who is assigned.

Command

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-sequence
Clone the repo
git clone --depth 1 https://github.com/DataSift-Ty-Personal/SiftStack
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 419 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 $0.00008 $0.00419
Opus 5 $0.00004 $0.00210
Sonnet 5 $0.00002 $0.00084
Haiku 4.5 $0.00001 $0.00042

Measured 2d ago against content hash 1077dc1b4bea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sift-sequence 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 2d 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-sequence.md · 37 lines

What it actually says

The user wants to build a Sift sequence. Follow this process:

  1. Read the skill file at ${CLAUDE_PLUGIN_ROOT}/skills/sift-operations/SKILL.md to load the domain routing table.

  2. Based on the user's description ($ARGUMENTS), determine which type of sequence they need and read the appropriate reference files:

    • For lead management: ${CLAUDE_PLUGIN_ROOT}/skills/sift-operations/references/lead-management-sequences.md
    • For acquisitions: ${CLAUDE_PLUGIN_ROOT}/skills/sift-operations/references/acquisitions-sequences.md
    • For board workflows: ${CLAUDE_PLUGIN_ROOT}/skills/sift-operations/references/board-workflows.md
    • For general ideation: ${CLAUDE_PLUGIN_ROOT}/skills/sift-operations/references/sequence-ideation.md
    • For drip integration: ${CLAUDE_PLUGIN_ROOT}/skills/sift-operations/references/drip-campaigns.md
  3. If the user's description is vague, use the ideation discovery questions to ask clarifying questions:

    • What event should trigger this?
    • What conditions should filter it?
    • What actions should happen?
    • Who should be assigned?
  4. Present the sequence configuration in a clear table format:

    • Trigger (with exact settings)
    • Condition(s) (with exact settings)
    • Action(s) (in order, with exact settings)
  5. Provide the step-by-step walkthrough for building it in Sift:

    • Navigate to Sequences → Create New Sequence
    • Add each component with exact field values
    • Name and save
  6. Include best practices and common pitfalls specific to this sequence type.

  7. If the sequence is complex (multi-sequence chain, board workflow), generate a markdown reference document saved to the workspace folder.

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. 2d ago First seen · 37 lines · 8 tokens per session scan A 1077dc1b4bea

Subscribe to this mod's changes

sift-sequence is a command published in the GitHub repository DataSift-Ty-Personal/SiftStack (21 stars, last pushed 4d ago), licensed MIT. It adds 8 tokens to every session and 419 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.