What is uf.cobalt-crush?

A command that delegates implementation work to the Cobalt-Crush developer agent, which follows the project’s instructions and active workflow.

Use it to implement a named task, fix a failing test, refactor code, or automatically continue the detected Speckit or OpenSpec workflow.

It gives implementation tasks a consistent process for checking project rules, specifications, conventions, and review feedback.

How unbound-force/gaze configures Claude Code and OpenCode

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.cobalt-crush.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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/unbound-force/gaze/uf.cobalt-crush/github.svg)](https://agentmods.dev/commands/unbound-force/gaze/uf.cobalt-crush)

Your own site

<a href="https://agentmods.dev/commands/unbound-force/gaze/uf.cobalt-crush"><img src="https://agentmods.dev/badge/commands/unbound-force/gaze/uf.cobalt-crush/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/unbound-force/gaze/uf.cobalt-crush"><img src="https://agentmods.dev/badge/commands/unbound-force/gaze/uf.cobalt-crush.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 999 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.

Model	Per session	Once invoked
Fable 5.1	$0.00045	$0.00999
Opus 5.5	$0.00018	$0.00400
Sonnet 5.5	$0.00009	$0.00200
Haiku 4.5	$0.00005	$0.00100

Measured 8d ago against content hash c89a4681f045, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

uf.cobalt-crush 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/commands/uf.cobalt-crush.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command: /uf.cobalt-crush

Description

Invoke the Cobalt-Crush developer persona to implement code with clean code principles, convention pack adherence, and feedback loop integration.

User Input

$ARGUMENTS

Usage

/uf.cobalt-crush [task description or instructions]
/uf.cobalt-crush                    # auto-detect workflow and implement

Examples

/uf.cobalt-crush implement T015 from tasks.md
/uf.cobalt-crush fix the failing test in internal/metrics/store_test.go
/uf.cobalt-crush refactor runMetrics to reduce complexity
/uf.cobalt-crush                    # detects speckit or openspec context

Instructions

When arguments are provided

Delegate to the cobalt-crush-dev agent using the Task tool with subagent_type: "cobalt-crush-dev". Pass the user's arguments as the task prompt. The agent will:

Read AGENTS.md, constitution, convention packs, and active specs
Apply its engineering philosophy (clean code, SOLID, TDD awareness)
Load convention packs from .opencode/uf/packs/
Check .uf/artifacts/ for Gaze/Divisor feedback
Execute the requested task following project conventions
Document design decisions in code comments

When no arguments are provided

Detect the active workflow and delegate the corresponding implementation command to the cobalt-crush-dev agent:

Check for a Speckit feature branch: Run .specify/scripts/bash/check-prerequisites.sh --json --paths-only from the repo root. If it succeeds and returns a FEATURE_DIR with a tasks.md, this is a Speckit strategic workflow. Read the full contents of .opencode/commands/speckit.implement.md and delegate it to the cobalt-crush-dev agent via the Task tool — pass the command file's instructions as the agent's prompt so the agent executes the implementation workflow.
Check for an OpenSpec active change: Look for directories under openspec/changes/ that contain a tasks.md file. If one exists, this is an OpenSpec tactical workflow. Validate branch: Run git rev-parse --abbrev-ref HEAD. The current branch must be opsx/<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>"

Read the full file on GitHub · 112 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.

1mo ago Changed d3ec3b5edb81
2mo ago First seen · 112 lines · 45 tokens per session scan A c89a4681f045

Subscribe to this mod's changes

uf.cobalt-crush is a command published in the GitHub repository unbound-force/gaze (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 999 once invoked, about $0.0002 per session on Opus 5.5. 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.

Building agents

uf.cobalt-crush next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
uf.cobalt-crushunbound-force/gaze	Command	4	yesterday	Apache-2.0	A	45	Claude Code, OpenCode
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code

gaze: Command for Claude Code