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/xeldaralz/everything-claude-unity/unity-ralphgit clone --depth 1 https://github.com/XeldarAlz/everything-claude-unityWrote 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/xeldaralz/everything-claude-unity/unity-ralph)<a href="https://agentmods.dev/commands/xeldaralz/everything-claude-unity/unity-ralph"><img src="https://agentmods.dev/badge/commands/xeldaralz/everything-claude-unity/unity-ralph.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 | $0.00035 | $0.01072 |
| Opus 5 | $0.00017 | $0.00536 |
| Sonnet 5 | $0.00007 | $0.00214 |
| Haiku 4.5 | $0.00003 | $0.00107 |
Grade A, and why
unity-ralph 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/unity-ralph — Persistent Verify-Fix Loop
Run a relentless verification loop that refuses to stop until the project is clean: $ARGUMENTS
Named after oh-my-claudecode's persistent execution mode. Where /unity-workflow runs the verifier once (up to 3 internal iterations), ralph runs it repeatedly until there are zero remaining issues — or until hitting the safety limit.
Configuration
Parse $ARGUMENTS for options:
| Option | Default | Description |
|---|---|---|
--max-iterations N |
10 | Maximum outer loop iterations (each runs verifier with up to 3 internal passes) |
--focus <path> |
all | Limit verification to a specific directory or file pattern |
--no-tests |
false | Skip test execution between iterations |
Everything after the flags is treated as context for the verifier (e.g., "focus on the new combat system").
Loop Protocol
Initialization
- Record the starting state:
git diff --statto capture baseline - Set
iteration = 0,previous_issues = "" - If
--focuswas provided, note the scope restriction
Each Iteration
iteration += 1
echo "Ralph iteration {iteration}/{max}: Starting verification pass..."
-
Invoke
unity-verifieragent via the Agent tool with:- The focus scope (if provided)
- Context from the previous iteration's remaining issues
- Instruction to report a structured summary at the end
-
Collect the verifier's final report — look for:
- "No auto-fixable issues found" or equivalent → SUCCESS, exit loop
- List of auto-fixed issues → note them
- List of remaining issues → capture for next iteration
-
Check console via MCP
read_console(if available) for compilation errors -
Run tests via MCP
run_tests(if available and--no-testsnot set) -
Progress report:
Ralph iteration {iteration}/{max}: {fixed_count} issues fixed, {remaining_count} remaining
Stall Detection
After each iteration, compare current remaining issues with previous_issues:
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 · 122 lines · 35 tokens per session scan A 93d0618e35e6
unity-ralph is a command published in the GitHub repository XeldarAlz/everything-claude-unity (21 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 1,072 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
init
Install the formatters this repository needs, with every command visible before it runs.
setup
Fetch Kobiton credentials from the authenticated MCP server and write them to /.kobiton/.credentials.
discuss
5-phase requirements-elicitation interview that produces an EARS-validated context/ .md.