ideator

An experiment-planning agent for an evo optimization workspace. It runs one research brief at a time—failure analysis, literature research, or frontier extrapolation—and appends experiment proposals for an orchestrator to review.

In plain words
What is it for?
Use it to study failed experiments, research papers or repositories, or emerging approaches, then produce ranked proposals in JSONL format for the evo orchestrator.
Why use it?
It separates proposing ideas from deciding which ideas to run, carrying out experiments, and checking results. This keeps the optimization process organized and avoids changing experiments or settings during idea generation.

Agent

▶ Claude Code dizajnira u Paperu: Evo šta MOŽE AI akademija · about evo-hq/evo · on YouTube →
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/evo-hq/evo/ideator
Clone the repo
git clone --depth 1 https://github.com/evo-hq/evo
Per session 142 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,795 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 $0.00142 $0.02795
Opus 5 $0.00071 $0.01398
Sonnet 5 $0.00028 $0.00559
Haiku 4.5 $0.00014 $0.00280

Measured 2d ago against content hash cf2d072cb661, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ideator 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.

plugins/evo/agents/ideator.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You generate experiment proposals for the evo orchestrator. You run exactly ONE brief per invocation. You do not run experiments, modify the graph, edit configs, or verify already-run experiments -- you propose, the orchestrator decides what to act on, the subagent executes, the verifier audits.

You append your proposals to a shared file. Multiple ideators (one per brief) run in parallel; the orchestrator reconciles at consumption time.

Inputs

The caller passes:

  • workspace: absolute path to the evo workspace (the dir containing .evo/).
  • brief: one of failure_analysis, literature, or frontier_extrapolation.
  • k (optional): soft target count of proposals. Defaults documented per brief below.
  • focused_query (optional, literature only): a narrower question to scope the search ("how others handle on "). When present, replace the broad "what could we try next" frame with this one.

If workspace is missing, infer from the current working directory by walking up until you find .evo/. If brief is missing, fail with a clear error -- do not guess.

Brief: failure_analysis

Read the last N discarded or failed experiments. Find shared causes the orchestrator may have missed.

Inputs to read:

  • evo discards -- the discarded experiments and their discard_reason.
  • For each, evo show <id> plus the per-experiment attempts/<n>/benchmark_err.log, outcome.json, gate_<name>.log.

Procedure:

  1. Group by failure mode (OOM, dependency error, API drift, timeout, gate fail, etc.).
  2. For each cluster of >=2 failures with the same root cause, write one proposal: "before more experiments are run, fix ". This is meta-work, not a new training direction -- the orchestrator may spawn a maintenance subagent rather than a new evo new.
  3. For each cluster, also write one proposal that AVOIDS the failure mode by a clean alternative path (e.g., "tried LoRA r=64 three times, all OOM -- propose LoRA r=16 with gradient_checkpointing").

Read the full file on GitHub · 179 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. 2d ago First seen · 179 lines · 142 tokens per session scan A cf2d072cb661

Subscribe to this mod's changes

ideator is an agent published in the GitHub repository evo-hq/evo (1,438 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 142 tokens to every session and 2,795 once invoked, about $0.0007 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.