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 commands/datasift-ty-personal/siftstack/sift-sequencegit clone --depth 1 https://github.com/DataSift-Ty-Personal/SiftStackWhat 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 | $0.00008 | $0.00419 |
| Opus 5 | $0.00004 | $0.00210 |
| Sonnet 5 | $0.00002 | $0.00084 |
| Haiku 4.5 | $0.00001 | $0.00042 |
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.
What it actually says
The user wants to build a Sift sequence. Follow this process:
-
Read the skill file at
${CLAUDE_PLUGIN_ROOT}/skills/sift-operations/SKILL.mdto load the domain routing table. -
Based on the user's description ($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
- For lead management:
-
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?
-
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)
-
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
-
Include best practices and common pitfalls specific to this sequence type.
-
If the sequence is complex (multi-sequence chain, board workflow), generate a markdown reference document saved to the workspace folder.
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.
- 2d ago First seen · 37 lines · 8 tokens per session scan A 1077dc1b4bea
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.