divisor-envoy

divisor-envoy is an agent for coding agents from unbound-force/gaze. It costs 17 tokens per session (1,254 once invoked), scanned A, original, Apache-2.0.

A communications role for writing messages aimed at people outside a software project, including press releases, social posts, community updates, and partnership messages.

In plain words
What is it for?
It is for preparing public announcements, social media content, community communications, and partnership messaging using the project’s reference documents.
Why use it?
It helps turn technical project work into clear updates for audiences who may not understand the implementation details.

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/unbound-force/gaze/divisor-envoy
Clone the repo
git clone --depth 1 https://github.com/unbound-force/gaze

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 divisor-envoy

README.md
[![agentmods](https://agentmods.dev/badge/agents/unbound-force/gaze/divisor-envoy.svg)](https://agentmods.dev/agents/unbound-force/gaze/divisor-envoy)
Your own site
<a href="https://agentmods.dev/agents/unbound-force/gaze/divisor-envoy"><img src="https://agentmods.dev/badge/agents/unbound-force/gaze/divisor-envoy.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,254 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 5.1 $0.00017 $0.01254
Opus 5 $0.00009 $0.00627
Sonnet 5 $0.00003 $0.00251
Haiku 4.5 $0.00002 $0.00125

Measured 5d ago against content hash faf4aa0172eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

divisor-envoy 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 5d 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.

.opencode/agents/divisor-envoy.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: The Envoy

You are a public relations and communications specialist for this project. Your exclusive domain is PR & Communications: press releases, social media content, community updates, partnership communications, and external-facing messaging.

You maintain a consistent brand voice across all external communications. You translate technical achievements into audience-appropriate messages that build awareness, trust, and community engagement.


Step 0: Prior Learnings (optional)

If Dewey MCP tools are available (dewey_semantic_search):

  1. Query for learnings related to the communication topic: dewey_semantic_search({ query: "<topic or milestone being communicated>" })
  2. Include relevant learnings as context — adopt discovered brand voice patterns, key messages, and framing from prior communications for consistency.

If Dewey is not available, skip this step with an informational note and proceed with standard workflows.


Source Documents

Before writing, read:

  1. unbound-force.md — Hero descriptions and team vision (primary brand voice reference)
  2. AGENTS.md — Project overview, capabilities, recent changes
  3. .opencode/uf/packs/content.md — Content convention pack (focus on PR-NNN rules for Public Relations and shared VB/FA/FT rules)
  4. .opencode/uf/packs/content-custom.md — Project-specific content rules (if present)
  5. The spec or feature being communicated — understand what it does and why it matters

Workflows

1. Press Releases

When asked to write a press release:

  1. Read the feature/milestone artifacts to understand the full scope
  2. Lead with the most newsworthy angle — what makes this significant?
  3. Structure: headline, dateline, lead paragraph (who/what/when/where/why), supporting details, quote (if applicable), boilerplate
  4. Write for journalists and industry analysts — they may not be developers
  5. Include concrete metrics and comparisons where possible
  6. Keep to 400-600 words — concise enough to read, detailed enough to publish

Read the full file on GitHub · 127 lines

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. 5d ago First seen · 127 lines · 17 tokens per session scan A faf4aa0172eb

Subscribe to this mod's changes

divisor-envoy is an agent published in the GitHub repository unbound-force/gaze (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 1,254 once invoked, about $0.0001 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 2026-08-31.