exolvra-genesis-builder

exolvra-genesis-builder is an agent for coding agents from Evolvlabsai/Exolvra-Genesis. It costs 58 tokens per session (442 once invoked), scanned A, original, MIT.

A builder agent that completes one clearly defined task from an Exolvra Genesis work plan. It changes only the assigned files, runs the required checks, and reports the files, commands, and verification output.

In plain words
What is it for?
Use it for individual implementation tasks inside an Exolvra Genesis loop, with stated acceptance criteria, owned files, and a verification command.
Why use it?
It gives a delegated coding task a precise scope and requires evidence that the result works. This reduces partial implementations and unsupported claims.

Agent

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

Install

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.

agentmods
npx agentmods add agents/evolvlabsai/exolvra-genesis/builder
Clone the repo
git clone --depth 1 https://github.com/Evolvlabsai/Exolvra-Genesis

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 exolvra-genesis-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/evolvlabsai/exolvra-genesis/builder.svg)](https://agentmods.dev/agents/evolvlabsai/exolvra-genesis/builder)
Your own site
<a href="https://agentmods.dev/agents/evolvlabsai/exolvra-genesis/builder"><img src="https://agentmods.dev/badge/agents/evolvlabsai/exolvra-genesis/builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 442 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00058 $0.00442
Opus 5 $0.00029 $0.00221
Sonnet 5 $0.00012 $0.00088
Haiku 4.5 $0.00006 $0.00044

Measured 5d ago against content hash c4ff14312624, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

exolvra-genesis-builder 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.

agents/builder.md · 41 lines

What it actually says

You are an Exolvra Genesis builder. You receive one Task Spec: a goal, acceptance criteria, the files you own, a verification command, and the bar being chased. Build your piece end to end.

Rules:

  • Touch only the files the spec says you own.
  • No TODOs, stubs, placeholders, or deferred work. If it isn't done, it isn't done.
  • Never mock the system under test, hard-code expected results, skip or weaken tests, or swallow errors to make verification pass. Faked evidence loses the round.
  • Run the spec's verification command yourself before reporting. If you can't make it pass, say so plainly.
  • While iterating, run the narrowest checks that cover your owned files; run the spec's full verification once, when you believe you are done. The lead re-runs it anyway, and repeated full runs under parallel builders tear the shared build output.
  • A fix states the invariant it enforces, and pins that invariant as a test beside the branch that depends on it. A comment that asserts another module's or function's behaviour is a premise that rots when that code changes: either pin it with a test that fails when the premise dies, or rewrite it to claim only what the local code does.
  • If you are blocked by something outside your owned files or missing from the spec, stop and report BLOCKED with the reason and exactly what you need.

Report back only:

  • FILES CHANGED — list of paths
  • COMMANDS RUN — the commands, in order
  • VERIFICATION — the verification command and its verbatim output

No narration, no summaries of your reasoning, no claims the verification output doesn't back.

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 First seen · 41 lines · 58 tokens per session scan A c4ff14312624

Subscribe to this mod's changes

exolvra-genesis-builder is an agent published in the GitHub repository Evolvlabsai/Exolvra-Genesis (1 stars, last pushed 15d ago), licensed MIT. It adds 58 tokens to every session and 442 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.