sequencer

A two-stage workflow for turning approved drafts into a timed sequence of messages, then sending that sequence after approval.

In plain words
What is it for?
Use it to plan and run multi-step outreach across channels, with business-day spacing, quiet hours, holidays, send windows, and reply-based stopping.
Why use it?
It prevents messages from being scheduled or sent before the plan is reviewed. It also handles timing rules and stops follow-ups when someone replies.

Agent

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 agents/onewave-ai/open-agent-stack/sequencer
Clone the repo
git clone --depth 1 https://github.com/OneWave-AI/open-agent-stack
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 385 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 $0.00000 $0.00385
Opus 5 $0.00000 $0.00192
Sonnet 5 $0.00000 $0.00077
Haiku 4.5 $0.00000 $0.00038

Measured yesterday against content hash c318ea4bb0ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sequencer 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 yesterday.

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.

orchestrators/sales-orchestrator/agents/sequencer.md · 51 lines

What it actually says

Sub-agent: sequencer

Role

Assemble approved drafts into a multi-touch cadence and, after the send gate, execute the schedule. Two phases: assemble, then execute.

Inputs

Assemble phase:

  • approved_drafts — Writer output approved at gate 2.
  • cadence_policy — touch count, spacing in business days, channel order, send window, stop-on-reply rule.

Execute phase:

  • approved_schedule — the cadence approved at gate 3.

Steps

Assemble:

  1. Build a touch plan per target: ordered touches with channel, send date, and the draft or follow-up for each.
  2. Generate follow-up touches that reference the prior message; do not repeat the opener verbatim.
  3. Apply quiet hours and the send window; skip weekends and holidays.
  4. Apply stop-on-reply so a reply halts remaining touches for that target.
  5. Return the full schedule for gate 3. Schedule nothing yet.

Execute (only after gate 3 approval): 6. Register each touch with the sending tool using keys from .env. 7. Record the provider message id and scheduled time per touch.

Output format

Assemble output, JSON array:

[
  {
    "email": "[email protected]",
    "touches": [
      {"step": 1, "channel": "email", "send_date": "2026-06-08", "ref": "draft"},
      {"step": 2, "channel": "email", "send_date": "2026-06-11", "ref": "followup-1"}
    ]
  }
]

Execute output: the same array with message_id and status per touch. Return a one-line summary: targets scheduled, total touches, send window.

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. yesterday First seen · 51 lines · 0 tokens per session scan A c318ea4bb0ee

Subscribe to this mod's changes

sequencer is an agent published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 385 tokens. 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 2026-08-31.

Related

Other agents, from other repositories

content-producer

Agent san xuat noi dung — viet script, copy, brief creator, lap lich noi dung.

minhnv0807/ai-business-skills · 23 tokens

personal-brand-builder

Agent xay dung thuong hieu ca nhan voi AI Avatar — chien luoc, content engine, monetization, community cho founder/coach/creator.

minhnv0807/ai-business-skills · 36 tokens

strategy-consultant

You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…

modu-ai/moai-cowork · 106 tokens

audit-geo

Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).

XuanRanL/loamwright-SEO-Skill · 44 tokens

schema-generator

Generates body JSON-LD (FAQPage + ItemList, ≥2 blocks) for a finished draft and WRITES it to the workspace schema.json. Distinct from schema-validator (which only inspects/validates). Dispatched by the optimize-phase schema-generator stage.

XuanRanL/loamwright-SEO-Skill · 58 tokens

autoresearch-test-runner

Test Runner Agent for AutoResearch. Executes the prompt/skill for real using all available tools (web search, APIs, file access). Operates with fresh context — knows NOTHING about eval criteria, assertions, iteration count, or optimization goals. This isolation ensures the main agent cannot influence output generation.

naveedharri/benai-skills · 65 tokens