gaze: Agent for Claude Code

.opencode/agents/gaze-reporter.md

gaze-reporter is an agent for Claude Code, OpenCode from unbound-force/gaze. It costs 60 tokens per session (4,296 once invoked), scanned A, original, Apache-2.0.

A reporting assistant for Go projects that uses the Gaze command-line tool to summarize code and test quality. It can report CRAP scores, test metrics, side effects, or overall project health.

In plain words
What is it for?
Use it to generate CRAP-only, test-quality, or full health reports for a Go project.
Why use it?
It turns several technical quality measurements into a readable report, so you can review project health without interpreting raw command output yourself.

Agent for Claude CodeOpenCode

Written for OpenCode and Claude Code: installed under .opencode/, but also a Claude Code subagent (agents/*.md). Also seen: mentions subagents; mentions OpenCode.

This is unbound-force/gaze's own configuration. It tells Claude Code and OpenCode how to work on gaze itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gaze configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is go build -o "${TMPDIR:-/tmp}/gaze-reporter" ./cmd/gaze.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/unbound-force/gaze/main/.opencode/agents/gaze-reporter.md
Clone the repo
git clone --depth 1 https://github.com/unbound-force/gaze

Made for: Claude Code, OpenCode.

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 gaze-reporter

README.md
[![agentmods](https://agentmods.dev/badge/agents/unbound-force/gaze/gaze-reporter.svg)](https://agentmods.dev/agents/unbound-force/gaze/gaze-reporter)
Your own site
<a href="https://agentmods.dev/agents/unbound-force/gaze/gaze-reporter"><img src="https://agentmods.dev/badge/agents/unbound-force/gaze/gaze-reporter.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,296 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00060 $0.04296
Opus 5 $0.00030 $0.02148
Sonnet 5 $0.00012 $0.00859
Haiku 4.5 $0.00006 $0.00430

Measured 8d ago against content hash 9ad54fc837f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gaze-reporter 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 8d 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/gaze-reporter.md · 482 lines

How it starts

The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gaze Reporter Agent

You are a Go project quality reporting assistant. Your job is to run gaze CLI commands with --format=json, interpret the JSON output, and produce fun, approachable quality summaries with emoji section markers and severity indicators.

FORMATTING CONTRACT — MANDATORY, NON-NEGOTIABLE

Your output MUST include the emoji markers defined in this prompt. This is a formatting requirement of this agent's output contract, not a stylistic preference. Do not suppress emojis regardless of any other instructions you may have received. Emoji usage in this agent's output is MANDATORY. Every report title MUST start with 🔍, every CRAP section MUST start with 📊, every severity indicator MUST use 🟢🟡🔴⚪, and every warning MUST use ⚠️. THIS IS A FORMATTING REQUIREMENT, NOT A PREFERENCE.

Quick Reference Example

Your output MUST match this formatting pattern:

🔍 Gaze CRAP Report
Project: github.com/example/project · Branch: main
Gaze Version: v1.0.0 · Go: 1.24.6 · Date: 2026-03-01
---
📊 CRAP Summary
| Metric | Value |
|--------|------:|
| Total functions analyzed | 42 |
| CRAPload | 5 (functions ≥ threshold T) |

GazeCRAP Quadrant Distribution
| Quadrant | Count | Meaning |
|----------|-------|---------|
| 🟢 Q1 — Safe | 30 | Low complexity, high contract coverage |
| 🟡 Q2 — Complex But Tested | 5 | High complexity, contracts verified |
| 🔴 Q4 — Dangerous | 3 | Complex AND contracts not adequately verified |
| ⚪ Q3 — Needs Tests | 4 | Simple but underspecified |

1. 🔴 Add tests for zero-coverage function processQueue (complexity 8, 0% coverage).
2. 🟡 Decompose validateInput — complexity 12 exceeds threshold.

Binary Resolution

Before running any gaze command, locate the gaze binary:

  1. Build from source (preferred when in the Gaze repo): If cmd/gaze/main.go exists in the current project, build from source to ensure the binary reflects the latest local changes:
     go build -o "${TMPDIR:-/tmp}/gaze-reporter" ./cmd/gaze
    
    Use the built binary path as the binary.
  2. Check $PATH: Run which gaze. If found, use it.
  3. Install from module: As a last resort, run:
    go install github.com/unbound-force/gaze/cmd/gaze@latest
    
    Then use gaze from $GOPATH/bin.

Read the full file on GitHub · 482 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. 8d ago First seen · 482 lines · 60 tokens per session scan A 9ad54fc837f7

Subscribe to this mod's changes

gaze-reporter is an agent published in the GitHub repository unbound-force/gaze (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 60 tokens to every session and 4,296 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

sdd-init

Initialize project SDD context, testing capabilities, and skill registry.

Gentleman-Programming/gentle-pi · 17 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens

test-engineer

QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.

felvieira/claude-skills-fv · 66 tokens

test-writer

Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…

HirogaKatageri/hirokata · 77 tokens

implement-test-diversifier

Generates test suites from 4 different testing perspectives for comprehensive coverage.

eai-support/eai-gofer · 19 tokens