experiment-loop

experiment-loop is a skill for Claude Code, Codex from event4u-app/agent-config. It costs 43 tokens per session (1,311 once invoked), scanned A, original, MIT.

An iteration loop for improving a measurable number, such as bundle size, runtime, query count, or violation count. It records each change and keeps or reverts it based on an evaluator's result.

In plain words
What is it for?
Use it to minimize or maximize a scalar metric through bounded change-and-check cycles, including deciding what to try when improvement stops.
Why use it?
It prevents gradual optimization work from keeping changes that make the result worse. It also preserves the loop's state so progress can be reviewed across sessions.

Skill for Claude CodeCodex

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

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is [evaluator-output](../../../docs/contracts/evaluator-output.md) verdict and the.

Good fit Use it to minimize or maximize a scalar metric through bounded change-and-check cycles, including deciding what to try when improvement stops.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/event4u-app/agent-config
agentmods
npx agentmods add skills/event4u-app/agent-config/experiment-loop

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 experiment-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/event4u-app/agent-config/experiment-loop/github.svg)](https://agentmods.dev/skills/event4u-app/agent-config/experiment-loop)
Your own site
<a href="https://agentmods.dev/skills/event4u-app/agent-config/experiment-loop"><img src="https://agentmods.dev/badge/skills/event4u-app/agent-config/experiment-loop/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for experiment-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/event4u-app/agent-config/experiment-loop"><img src="https://agentmods.dev/badge/skills/event4u-app/agent-config/experiment-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,311 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00043 $0.01311
Opus 5 $0.00022 $0.00656
Sonnet 5 $0.00009 $0.00262
Haiku 4.5 $0.00004 $0.00131

Measured 7d ago against content hash 754ff6dff0fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

experiment-loop 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 7d 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.

src/skills/experiment-loop/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

experiment-loop

A bounded change → commit → evaluate → keep-or-revert cycle against a scalar metric, where the decision input is an evaluator-output verdict and the loop's entire state lives in an append-only register on disk.

This file routes. The protocol, the register format, and the pivot ladder are reference files loaded on demand — a loop doctrine read in full on every session that merely mentions optimization is a payload nobody asked for.

Need Load
The iteration protocol and its two exit conditions references/protocol.md
The register's row shape and write ordering references/register-format.md
What to do when the metric stops moving references/pivot-ladder.md

When to use

  • The goal is expressible as "minimize X" or "maximize X" against a mechanical verifier — bundle size, violation count, query count, runtime.
  • A verifier already emits, or can be wrapped to emit, the evaluator-output contract. Wrapping is usually free: three of this repo's verifiers were wrapped with zero changes to any of them.

Do NOT use when:

  • The target is a known end state, not a number — "make the tests pass" has a destination, so use verify-repair-loop, which converges toward it. This skill has no destination; it has a direction.
  • The verdict is subjective craft — no scalar, nothing to optimize.
  • The metric is a proxy nobody agreed on. Optimizing an unowned proxy is how a loop makes a system worse while its number improves.

The Iron Law

THE METRIC IS NEVER SOVEREIGN. `pass` IS.
KEEP ONLY ON `pass && score > baseline`. A CHANGE THAT IMPROVES THE NUMBER
AND BREAKS BEHAVIOUR IS REVERTED — MEASURED, NOT ASSUMED.
COMMIT BEFORE YOU EVALUATE, SO EVERY REVERT IS A GIT OPERATION.
THE REGISTER IS WRITTEN BEFORE THE ACTION IT RECORDS, NEVER AFTER.
STATE LIVES ON DISK AND IS RE-READ EACH CYCLE — NEVER IN THE CONVERSATION.

Read the full file on GitHub · 117 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 117 lines · 43 tokens per session scan A 754ff6dff0fe

Subscribe to this mod's changes

experiment-loop is a skill published in the GitHub repository event4u-app/agent-config (10 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,311 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

save-progress

Save current project task progress to local task state file for cross-session continuity. Use when the user asks to save progress, uses an equivalent localized trigger phrase, the session is interrupted, or the user wants to resume work later. Writes to .claude/project-task-state.json so next session can load it via…

KimYx0207/Meta_Kim · 65 tokens

same-set-reusable-flow-for-project-file-inventor

Reusable MetaKim file inventory classification flow. It helps separate durable sources, generated evidence, runtime mirrors, temporary state, and risky unknowns before cleanup or commit.

KimYx0207/Meta_Kim · 45 tokens

meta-theory

MetaKim executable governance dispatcher. It classifies the run, loads only needed references, preserves foundational capabilities and runtime-native abilities, routes owner + weapon + dependency + runtime + OS + verification, and closes only with evidence, intent acceptance, and writeback decision.

KimYx0207/Meta_Kim · 57 tokens

starreel-drama-production

Operating skill for any AI agent driving the StarReel short-drama production pipeline (script → rewrite → extract → portraits + sheets → storyboards → frames → video → voiceover → final cut) over MCP or REST. Covers the ordered workflow, the entry-point decision table (which channel each kind of customer material…

waydaxp/starreel-mcp · 102 tokens

seedance-20

Generate and direct cinematic AI videos with Seedance 2.0 (ByteDance/Dreamina/Jimeng). Covers text-to-video, image-to-video, video-to-video, and reference-to-video workflows with @Tag asset references, multi-character scenes, audio design, and post-processing. Use when making AI video, writing Seedance prompts…

Kingdaddy007/my-os · 96 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens