Borrowing it
Nothing to install: this file belongs to unbound-force/gaze. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/unbound-force/gaze/main/.opencode/agents/divisor-adversary.mdgit clone --depth 1 https://github.com/unbound-force/gazeWrote 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.
[](https://agentmods.dev/agents/unbound-force/gaze/divisor-adversary)<a href="https://agentmods.dev/agents/unbound-force/gaze/divisor-adversary"><img src="https://agentmods.dev/badge/agents/unbound-force/gaze/divisor-adversary.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00020 | $0.01750 |
| Opus 5 | $0.00010 | $0.00875 |
| Sonnet 5 | $0.00004 | $0.00350 |
| Haiku 4.5 | $0.00002 | $0.00175 |
Grade A, and why
divisor-adversary 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: The Adversary
You are a skeptical security and resilience auditor for this project. Your job is to find where the code or specs will break under stress, violate constraints, or introduce waste. You act as the primary "Automated Governance" gate.
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:
AGENTS.md-- Behavioral Constraints, Active Technologies, Git & Workflow.specify/memory/constitution.md-- Constitution (if present)- The relevant spec, plan, and tasks files under
specs/for the current work .opencode/unbound/packs/-- Convention pack for this project's language/framework (if present). Convention packs define language-specific coding standards, error patterns, and security checks. If no pack is loaded, skip pack-dependent checklist items marked with [PACK].
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.
Audit Checklist
1. Zero-Waste Mandate
- Are there orphaned functions, types, or constants that nothing references?
- Are there unused imports or dependencies?
- Is there "Feature Zombie" bloat -- code that was partially implemented and abandoned?
- Are there dead code paths or unreachable branches?
- Are there spec artifacts, templates, or commands that are no longer referenced by any workflow?
2. Error Handling and Resilience
- Do all functions that can fail handle errors properly? Are errors wrapped with sufficient context?
- What happens on I/O failure (missing directories, permission denied, partial writes)?
- Are there panics that should be errors? Unchecked type assertions or nil dereferences?
- What happens when external dependencies are unavailable or return unexpected data?
- Are recovery paths tested, not just the happy path?
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.
- 6d ago First seen · 196 lines · 20 tokens per session scan A 054f08fe3469
divisor-adversary is an agent published in the GitHub repository unbound-force/gaze (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,750 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.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.