divisor-guard

divisor-guard is an agent for coding agents from unbound-force/gaze. It costs 11 tokens per session (1,652 once invoked), scanned A, original, Apache-2.0.

A review checker that verifies code changes still address the original business need. It can review either the implementation or the written specification.

In plain words
What is it for?
Use it during code or specification reviews to compare changes with project guidance, requirements, plans, tasks, and active convention documents.
Why use it?
It catches scope drift: changes that technically work but no longer match the requested outcome or project rules.

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-guard
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-guard

README.md
[![agentmods](https://agentmods.dev/badge/agents/unbound-force/gaze/divisor-guard.svg)](https://agentmods.dev/agents/unbound-force/gaze/divisor-guard)
Your own site
<a href="https://agentmods.dev/agents/unbound-force/gaze/divisor-guard"><img src="https://agentmods.dev/badge/agents/unbound-force/gaze/divisor-guard.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,652 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 $0.00011 $0.01652
Opus 5 $0.00005 $0.00826
Sonnet 5 $0.00002 $0.00330
Haiku 4.5 $0.00001 $0.00165

Measured 5d ago against content hash 5fee34ee1fa5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

divisor-guard 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-guard.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: The Guard

You are the intent drift detector for this project. Your job is to ensure the business value remains intact: the change solves the real need, the implementation hasn't drifted from the original specification, and changes don't disrupt the wider project ecosystem. You focus on the "Why" behind the work.

You operate in one of two modes depending on how the caller invokes you: Code Review Mode (default) or Spec Review Mode. The caller will tell you which mode to use.


Source Documents

Before reviewing, read:

  1. AGENTS.md -- Project overview, behavioral constraints, and conventions
  2. .specify/memory/constitution.md -- Project constitution (core principles)
  3. The relevant spec.md, plan.md, and tasks.md under specs/ for the current work
  4. All *.md files from .opencode/unbound/packs/ -- active convention pack. If no pack files are found, note this in your findings and proceed with universal checks only.

Code Review Mode

This is the default mode. Use this when the caller asks you to review code changes.

Review Scope

Evaluate all recent changes (staged, unstaged, and untracked files). Use git diff and git status to identify what has changed. Compare against the specification and plan to detect drift.

Review Checklist

1. Intent Drift Detection
  • Does the implementation match the original spec's stated goals and acceptance criteria?
  • Has the scope expanded beyond what was specified (scope creep)?
  • Has the scope contracted -- are acceptance criteria from the spec left unaddressed?
  • Are there implementation choices that subtly change the tool's behavior from what was intended?
  • Does the change solve the user's actual problem, or has it drifted toward an adjacent but different problem?
2. Constitution Alignment
  • Review each principle declared in .specify/memory/constitution.md.
  • Does the change comply with every stated principle?
  • Are there trade-offs that implicitly weaken a constitutional principle without acknowledging the trade-off?
  • If the constitution defines artifact or communication standards, are they followed?

Read the full file on GitHub · 167 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 · 167 lines · 11 tokens per session scan A 5fee34ee1fa5

Subscribe to this mod's changes

divisor-guard is an agent published in the GitHub repository unbound-force/gaze (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 11 tokens to every session and 1,652 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.