iteration_plan

iteration_plan is a skill for Claude Code, Codex from simple-agent-lab/AutoTrainess. It costs 17 tokens per session (309 once invoked), scanned A, original, MIT.

A guide for planning the next experiment iteration from evidence gathered in earlier experiments. It separates the previous problems, the new objective, the planned changes, and the definition of success.

In plain words
What is it for?
Use it to define the next experiment's goal, decide whether to change the data, training, or both, and give concrete instructions to the work that follows.
Why use it?
It keeps experimentation focused on the most important observed problem instead of changing many things without a clear reason.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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 skills/simple-agent-lab/autotrainess/iteration_plan
Any agent
npx skills add simple-agent-lab/AutoTrainess --skill iteration_plan
Clone the repo
git clone --depth 1 https://github.com/simple-agent-lab/AutoTrainess

Made for: Claude Code, Codex.

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 iteration_plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/simple-agent-lab/autotrainess/iteration_plan.svg)](https://agentmods.dev/skills/simple-agent-lab/autotrainess/iteration_plan)
Your own site
<a href="https://agentmods.dev/skills/simple-agent-lab/autotrainess/iteration_plan"><img src="https://agentmods.dev/badge/skills/simple-agent-lab/autotrainess/iteration_plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 309 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 $0.00017 $0.00309
Opus 5 $0.00009 $0.00154
Sonnet 5 $0.00003 $0.00062
Haiku 4.5 $0.00002 $0.00031

Measured 6d ago against content hash ab5e8663da37, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

iteration_plan 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 6d 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.

autotrainhub/iteration_plan/SKILL.md · 39 lines

What it actually says

iteration_plan

Purpose

Define a clear goal and concrete action plan for the current experiment iteration based on real evidence from previous experiments.

Inputs

  • Results from previous experiments.
  • Prior evaluation evidence and analysis.
  • The current training and data context available in the workspace.

Required outputs

  • The main problems observed in previous experiments.
  • The main objective of the current iteration.
  • The changes planned for the current iteration.
  • Whether this iteration mainly changes data, training, or both.
  • The outcome that will count as success.
  • Concise guidance for downstream data or training work.

Rules

  • Base the plan on real evidence from previous experiments rather than speculation.
  • Focus on the main objective of the current iteration rather than trying to address every issue at once.
  • Separate previous problems, current objective, planned changes, and success criteria clearly.
  • Define the direction for the current iteration, but do not directly execute data construction or training in this skill.
  • Keep the plan concrete enough that downstream skills can act on it.

Procedure

  1. Review previous experiment results and identify the main problems.
  2. Decide what the current iteration is mainly trying to improve.
  3. Define the main changes to make in this iteration.
  4. State what outcome will count as success for this iteration.
  5. Provide concise guidance for downstream data and training work.
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. 6d ago First seen · 39 lines · 17 tokens per session scan A ab5e8663da37

Subscribe to this mod's changes

iteration_plan is a skill published in the GitHub repository simple-agent-lab/AutoTrainess (21 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 309 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.