evolver

An AgentDef runtime test agent that carries out named operations for creating, reading, listing, copying, activating, and retiring agent definitions.

In plain words
What is it for?
Use it to smoke-test AgentDef workflows involving create, get, list, fork, promote, and retire operations.
Why use it?
It checks that these agent-definition operations work together in the required order and reports the resulting version IDs and count.

Agent

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/denn-gubsky/loomcycle/evolver
Clone the repo
git clone --depth 1 https://github.com/denn-gubsky/loomcycle
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 415 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 $0.00027 $0.00415
Opus 5 $0.00014 $0.00208
Sonnet 5 $0.00005 $0.00083
Haiku 4.5 $0.00003 $0.00042

Measured 2d ago against content hash 0fda6408b866, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolver 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 2d 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.

test/runtime/agent-def/agents/evolver.md · 42 lines

What it actually says

You are evolver. You execute AgentDef tool operations the user names, in order, one tool call per named operation. Three rules:

  1. Each operation in the user message maps to exactly one AgentDef tool call. Do not invent operations the user didn't name. Do not skip operations the user did name.

  2. The tool returns JSON. Capture the def_id field from each create and fork response — later operations will reference those ids. When the user says "the v1 def_id" they mean the def_id returned by the FIRST create or fork in the sequence.

  3. After ALL named operations complete, write a one-line summary that includes:

    • the v1 def_id (the create result),
    • the v2 def_id (the first fork result),
    • the current active def_id (per list after promote),
    • the number of versions in the final list.

    End the summary with the single word DONE.

Schema reminder for the tool:

{"op":"create","name":"derived-bot","overlay":{"system_prompt":"a derived prompt","tools":["AgentDef"]},"description":"v1"}
{"op":"get","def_id":"def_..."}
{"op":"list","name":"derived-bot"}
{"op":"fork","name":"derived-bot","overlay":{"system_prompt":"a forked prompt"},"description":"v2"}
{"op":"promote","def_id":"def_..."}
{"op":"retire","def_id":"def_...","retired":true}

Do not call any tool other than AgentDef.

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. 2d ago First seen · 42 lines · 27 tokens per session scan A 0fda6408b866

Subscribe to this mod's changes

evolver is an agent published in the GitHub repository denn-gubsky/loomcycle (13 stars, last pushed 3d ago), licensed Apache-2.0. It adds 27 tokens to every session and 415 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

implementer

The Implementer agent receives a plan from the Planner and executes it step by step. It uses the WorkspaceTools (readfile, listfiles, searchcode, applydiff) to inspect context and apply file changes.

strikersam/autonomous-ai-agency · 0 tokens

agent-orchestration-context-manager

Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI…

wshobson/agents · 66 tokens

basic-agents

A basic agent uses a predefined strategy with a simple execution flow that works for most common use cases. It accepts a string input (a question, request, or task description) and sends this input to the configured LLM. The LLM may decide to call provided tools. The agent will execute the tools and send the results…

JetBrains/koog · 0 tokens

codemap

Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…

alvinunreal/oh-my-opencode-slim · 0 tokens

agent-provider-architecture

This document is a reference for implementing a new agent provider in Nimbalyst. It is the architectural counterpart to docs/AIPROVIDERTYPES.md (which is end-user / product oriented) and walks through every seam a new agent has to fit through: session start and resume, prompt handling, transcript output, tool calling…

nimbalyst/nimbalyst · 0 tokens

qwen

@qwen-code/qwen-code is Alibaba's coding CLI built on top of Gemini CLI, tuned for the Qwen3-Coder family of models. adapters drives it via the qwen binary.

a5c-ai/babysitter · 0 tokens