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.
npx agentmods add commands/unbound-force/gaze/gaze-fixgit 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/commands/unbound-force/gaze/gaze-fix)<a href="https://agentmods.dev/commands/unbound-force/gaze/gaze-fix"><img src="https://agentmods.dev/badge/commands/unbound-force/gaze/gaze-fix.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 | $0.00057 | $0.01661 |
| Opus 5 | $0.00028 | $0.00830 |
| Sonnet 5 | $0.00011 | $0.00332 |
| Haiku 4.5 | $0.00006 | $0.00166 |
Grade A, and why
gaze-fix 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Description
Dual-mode command. Without arguments, detects the active implementation
workflow (Speckit or OpenSpec) and runs it. With arguments, performs
batch remediation — reads gaze analysis data, identifies functions
needing tests or documentation, and generates compilable fixes via
the gaze-test-generator agent.
Usage
/gaze fix # auto-detect workflow and implement
/gaze fix [package-pattern] # batch test generation
/gaze fix --strategy=add_tests [pattern]
/gaze fix --top=5 [pattern]
/gaze fix --dry-run [pattern]
Options
| Option | Description |
|---|---|
[pattern] |
Go package pattern (default: ./...) |
--strategy=X |
Filter to one strategy: add_tests, add_assertions, add_docs, decompose_and_test |
--top=N |
Process only the top N functions by CRAP score |
--dry-run |
Show what would be generated without writing files |
Instructions
When no arguments are provided
Detect the active workflow and delegate to the corresponding implementation command:
-
Check for a Speckit feature branch: Run
.specify/scripts/bash/check-prerequisites.sh --json --paths-onlyfrom the repo root. If it succeeds and returns aFEATURE_DIRwith atasks.md, this is a Speckit strategic workflow. Read the full contents of.opencode/commands/speckit.implement.mdand execute its instructions directly — follow the implementation workflow it describes. -
Check for an OpenSpec active change: Look for directories under
openspec/changes/(excludingarchive/) that contain atasks.mdfile. If one exists, this is an OpenSpec tactical workflow. Validate branch: Rungit rev-parse --abbrev-ref HEAD. The current branch must beopsx/<change-name>where<change-name>matches the detected change directory name. If not on the correct branch, STOP with error:"OpenSpec change
<name>detected but you are on branch<current-branch>. Run:git checkout opsx/<name>"
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.
- 5d ago First seen · 187 lines · 57 tokens per session scan A 10d4a98bd729
gaze-fix is a command published in the GitHub repository unbound-force/gaze (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 1,661 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.
Other commands, from other repositories
test-gen
Generate comprehensive Go tests with table-driven patterns.
generate-tests
Generate unit or integration tests for Go code following project patterns and coverage targets.
golang-test-review
Use when reviewing Go test code (new or changed test.go files, test harnesses, fixtures, or test tooling) for a Go-test-expert pass — behavior-over-surface, determinism, parallel-safety, build-tag correctness, and harness reuse. Complements the general code-reviewer with test-specific rigor.
golang-development:test
Generate comprehensive tests including unit tests, table-driven tests, benchmarks, and examples with high coverage.
generate-tests
为 Golang/trpc-go 项目生成包含单元测试、集成测试和边界情况覆盖的全面测试套件.
cli-patterns
Reference patterns for implementing CLI commands in internal/cli/.