gaze: Command for Claude Code

.opencode/commands/uf.unleash.md

uf.unleash is a command for Claude Code, OpenCode from unbound-force/gaze. It costs 60 tokens per session (6,345 once invoked), scanned A, original, Apache-2.0.

A command that runs an end-to-end software change workflow for Speckit or OpenSpec, from clarifying the idea and writing the plan through implementation, review, and demo instructions.

In plain words
What is it for?
Use it to take a specification from an early draft to demo-ready code, including task generation, specification review, implementation, code review, and retrospective notes.
Why use it?
It coordinates the repeated planning and review steps and can resume from recorded progress when human judgment is needed.

Command for Claude CodeOpenCode

Written for OpenCode and Claude Code: installed under .opencode/, but also a Claude Code command (commands/*.md). Also seen: 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 →

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/commands/uf.unleash.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 uf.unleash

README.md
[![agentmods](https://agentmods.dev/badge/commands/unbound-force/gaze/uf.unleash/github.svg)](https://agentmods.dev/commands/unbound-force/gaze/uf.unleash)
Your own site
<a href="https://agentmods.dev/commands/unbound-force/gaze/uf.unleash"><img src="https://agentmods.dev/badge/commands/unbound-force/gaze/uf.unleash/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for uf.unleash

Your own site · 80×15
<a href="https://agentmods.dev/commands/unbound-force/gaze/uf.unleash"><img src="https://agentmods.dev/badge/commands/unbound-force/gaze/uf.unleash.svg" alt="Reviewed on agentmods" width="80" 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 6,345 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 $0.06345
Opus 5 $0.00030 $0.03173
Sonnet 5 $0.00012 $0.01269
Haiku 4.5 $0.00006 $0.00634

Measured 5d ago against content hash 5a3663ee81c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

uf.unleash 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/commands/uf.unleash.md · 774 lines

How it starts

The opening of the file, as written. The whole thing — 774 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command: /uf.unleash

Description

Autonomous pipeline execution for both Speckit (strategic) and OpenSpec (tactical) changes. Takes a spec from draft to demo-ready code in a single command. Orchestrates 8 steps: clarify, plan, tasks, spec review, implement, code review, retrospective, and demo. Exits gracefully when human judgment is needed and resumes from where it left off on re-run.

Usage

/uf.unleash

Instructions

SESSION-RESUME GUARD: If you are resuming this command after context compression or a session restart, STOP and re-read this entire template before continuing. Do NOT infer which steps are complete from compressed context summaries. Only filesystem markers are authoritative for resumability:

  • Task checkboxes ([x] vs [ ]) in tasks.md
  • <!-- spec-review: passed --> in tasks.md
  • <!-- code-review: passed --> in tasks.md

Maintain the execution checklist below using the Edit tool. Update it in-place as each step, phase, or iteration completes. This is your live state record.

Execution Checklist -- update in-place with Edit tool:

- [ ] Step 0: Startup Cleanup
- [ ] Step 1: Branch Safety Gate
- [ ] Step 2: Resumability Detection
- [ ] Step 3: Clarify (Step 1)
- [ ] Step 4: Plan (Step 2)
- [ ] Step 5: Tasks (Step 3)
- [ ] Step 6: Spec Review (Step 4) -- iteration: 0/3
- [ ] Step 7: Implement (Step 5) -- phase: 0/N, batch: 0/N, workers: 0/N
- [ ] Step 8: Code Review (Step 6) -- iteration: 0/3
- [ ] Step 9: Retrospective (Step 7)
- [ ] Step 10: Demo (Step 8)

0. Startup Cleanup

Before any pipeline logic, clean up stale worktrees from previous interrupted runs:

  1. Call swarm_worktree_list with the project path.
  2. If any worktrees exist, call swarm_worktree_cleanup with cleanup_all: true to remove them.
  3. This cleanup does NOT affect resumability -- spec.md, plan.md, tasks.md, and task checkboxes live in the main working directory, not in worktrees.

Read the full file on GitHub · 774 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 Changed · +33 lines 5a3663ee81c1
  2. 9d ago First seen · 741 lines · 60 tokens per session scan A 2ee13399d1fd

Subscribe to this mod's changes

uf.unleash is a command published in the GitHub repository unbound-force/gaze (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 60 tokens to every session and 6,345 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.