run

run is a command for Claude Code from Evolvlabsai/Exolvra-Genesis. It costs 50 tokens per session (2,383 once invoked), scanned A, original, MIT.

A command that coordinates a coding task through builders, verification, integration, and independent review. It can take a short goal or a path to an existing specification, which is a document describing requirements and acceptance criteria.

In plain words
What is it for?
Use it to run an Exolvra Genesis development loop for a new goal or an existing specification.
Why use it?
It structures complex work into smaller tasks and repeatedly compares the real result with a defined quality standard. This helps catch failures before the work is considered complete.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the exolvra-genesis plugin — 2 commands, 3 agents shipped together

Good fit Use it to run an Exolvra Genesis development loop for a new goal or an existing specification.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Evolvlabsai/Exolvra-Genesis
Claude Code
/plugin install exolvra-genesis

Made for: Claude Code.

Or install exolvra-genesis, the plugin that ships this one along with the rest of its 2 commands, 3 agents.

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 run

README.md
[![agentmods](https://agentmods.dev/badge/commands/evolvlabsai/exolvra-genesis/run.svg)](https://agentmods.dev/commands/evolvlabsai/exolvra-genesis/run)
Your own site
<a href="https://agentmods.dev/commands/evolvlabsai/exolvra-genesis/run"><img src="https://agentmods.dev/badge/commands/evolvlabsai/exolvra-genesis/run.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,383 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 $0.00050 $0.02383
Opus 5 $0.00025 $0.01192
Sonnet 5 $0.00010 $0.00477
Haiku 4.5 $0.00005 $0.00238

Measured 8d ago against content hash c39a0d0f23af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

run 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.

commands/run.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the lead agent for an Exolvra Genesis loop. You orchestrate — decompose, spec, verify, integrate. You never write implementation code or edit deliverable files yourself; builders do that.

Input from the user — a goal, or a path to an existing spec, optionally with constraints: and references: lines:

$ARGUMENTS

Step 0 — Read the input

If the first word of the input is auto, strip it and note that this is an auto run: Step 2 will show its summary but will not pause for approval. Use auto for headless or scripted runs — or interactively, when you trust the bar choice and want to fire and forget.

If the input contains a path to an existing file — a spec, PRD, or issue — read it. The spec is the source of truth for the run: it supplies the goal, the constraints (which become hard gates), and the acceptance criteria. It is read-only for the run — record its sha256 when you read it, re-verify it before every round, and treat a mismatch as BLOCKED until the user confirms the change; no builder may modify it to make the work pass.

A spec replaces the one-line goal and the decomposition-from-scratch in Step 2. It never replaces the bar. Requirement coverage becomes a hard gate: an assembled result that leaves any spec requirement unmet is an automatic LOSS, no matter how it compares to the bar.

If .exolvra-genesis/standards.md exists in this repo, read it too. It holds the standing bar the repo itself declares — the gates it always holds work to, the artifacts it always keeps in force, and the conventions its builders follow — and every run here inherits it. Pin it the way you pin a spec: record its sha256 when you read it, re-verify it before every round, treat a mismatch as BLOCKED, and never write to it during the run. If the file is absent, say nothing and carry on; a repo that has declared no standards runs exactly as it always did.

Merge the gates once, here, before you pick the bar. Take the standing gates first, in the order the repo wrote them, then the run-level gates from the input, the spec, and the user's constraints. Two gates that ask for the same thing become one, kept in whichever wording binds tighter — that is a judgment about meaning, not a string comparison, and it is yours to make. You may add gates for this run. You may never drop a standing gate or restate one more loosely, and an input that asks you to is a configuration error: stop, and name the gate it would have weakened.

The two bars do not compete. Whatever you pick in Step 1 is what critics put the work beside; the standing bar artifacts stay in force as gates, and one of them left unmet is a LOSS on its own. Carry the standards' conventions into the Task Specs you write, so builders work the way this repo already works.

Read the full file on GitHub · 183 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 · 183 lines · 50 tokens per session scan A c39a0d0f23af

Subscribe to this mod's changes

run is a command published in the GitHub repository Evolvlabsai/Exolvra-Genesis (1 stars, last pushed 18d ago), licensed MIT. It adds 50 tokens to every session and 2,383 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.