experiment_loop

experiment_loop is a skill for Claude Code from AnirudhaRamesh/experiment-automation-claude-code-plugin. It costs 28 tokens per session (678 once invoked), scanned B, original, no licence file.

An iterative development loop that runs experiments in an isolated Git worktree, a separate working copy of a repository. It diagnoses failures, applies fixes, and tries again.

In plain words
What is it for?
Running experiments, investigating failed attempts, applying corrections, and retrying in a separate worktree.
Why use it?
It keeps experiments separate from the main working copy while repeating failure-and-fix cycles automatically.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter.

Part of the aichor-experiment-automation plugin — 9 skills, 6 agents shipped together

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/anirudharamesh/experiment-automation-claude-code-plugin/experiment-loop
Any agent
npx skills add AnirudhaRamesh/experiment-automation-claude-code-plugin --skill experiment-loop
Clone the repo
git clone --depth 1 https://github.com/AnirudhaRamesh/experiment-automation-claude-code-plugin

Made for: Claude Code.

Or install aichor-experiment-automation, the plugin that ships this one along with the rest of its 9 skills, 6 agents.

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/anirudharamesh/experiment-automation-claude-code-plugin/experiment-loop.svg)](https://agentmods.dev/skills/anirudharamesh/experiment-automation-claude-code-plugin/experiment-loop)
Your own site
<a href="https://agentmods.dev/skills/anirudharamesh/experiment-automation-claude-code-plugin/experiment-loop"><img src="https://agentmods.dev/badge/skills/anirudharamesh/experiment-automation-claude-code-plugin/experiment-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 678 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin unknown 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 $0.00028 $0.00678
Opus 5 $0.00014 $0.00339
Sonnet 5 $0.00006 $0.00136
Haiku 4.5 $0.00003 $0.00068

Measured 6d ago against content hash e02093c8ffc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

experiment_loop scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

2. How to **monitor progress**: `tail -f .claude/loop-state/<loop-id>/progress.log`
skills/experiment-loop/SKILL.md · 68 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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 · 68 lines · 28 tokens per session scan B e02093c8ffc3

Subscribe to this mod's changes

experiment_loop is a skill published in the GitHub repository AnirudhaRamesh/experiment-automation-claude-code-plugin (4 stars, last pushed 6mo ago), with no licence file. It adds 28 tokens to every session and 678 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

agent-merge-conflict-arbiter

Neutral arbiter for merge conflicts between two agents.

NousResearch/hermes-agent · 19 tokens

git-advanced-workflows

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

wshobson/agents · 54 tokens

bisect

Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.

chromium/chromium · 52 tokens

mantis-critic

Assesses the production viability of findings, filtering out debug-only features and assertion traps. Use when findings have been validated and you need to confirm they are triggerable in production release builds (with assertions disabled). Don't use for writing reproduction scripts or patches.

google/mantis · 55 tokens

hotpath_bump

Bump the hotpath version number across the workspace and related files. Updates crate versions in Cargo.toml files (exact patch version) and version references in the backend middleware, hotpathinit skill, and README (major.minor only). Use when the user wants to bump, bump the version, or release a new hotpath…

pawurb/hotpath-rs · 73 tokens

triaging-merge-queue-failures

Decision procedure for a PR that failed or was removed from the Trunk merge queue: classify the kick (superseded by a newer commit, not mergeable, a gate that failed on a cancelled run, real failure, one-off flake, or repo-wide flaky/infra issue) and take the matching action (wait, hold and fix, requeue once, or…

PostHog/posthog-foss · 180 tokens