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.
/plugin marketplace add Evolvlabsai/Exolvra-Genesis/plugin install exolvra-genesisWrote 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/evolvlabsai/exolvra-genesis/run)<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>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 | $0.00050 | $0.02383 |
| Opus 5 | $0.00025 | $0.01192 |
| Sonnet 5 | $0.00010 | $0.00477 |
| Haiku 4.5 | $0.00005 | $0.00238 |
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.
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.
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.
- 8d ago First seen · 183 lines · 50 tokens per session scan A c39a0d0f23af
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.
Other commands, from other repositories
update
Update Megazord to the latest version.
debug
Systematic four-phase debugging (reproduce, isolate, root-cause, fix).
discuss
Socratic brainstorming to explore approaches before implementation.
go
Execute the current phase plan with subagent delegation.
help
Show all available Megazord skills with descriptions and usage examples.
init
Initialize a Megazord project with configuration and planning structure.