optim-agent
Act as the sampler inside any coding-agent session: Claude Code, Codex, OpenCode/OpenClaw, or another agent that can read project files and run shell commands.
Connecting the steps of a workflow
What it does
Act as the sampler inside any coding-agent session: Claude Code, Codex, OpenCode/OpenClaw, or another agent that can read project files and run shell commands.
Read more
Read the project to understand parameter meaning and interactions, propose one configuration, run the real evaluator, and record the result through optim-agent's ask/tell API. Let the measured objective, not the agent's intuition, decide what works.
Use when the user wants to optimize configurable system parameters against a measurable scalar objective, especially for model training,…
You don’t need to name it. Ask for the job in your own words — your AI loads the skill when the request matches.
What it can touch
Includes 31 scripts
Your AI can run these when the skill is used — on your computer in a coding tool (which asks first unless you have told it not to), or in the AI’s own sandbox in Claude and ChatGPT.
How we know
Found in the skill’s folder: docs/optim-plans/2026-07-27-summary-agent-and-table-logging-retry/WORKER_BLOCKED.TASK-001.reporting.py, examples/cifar10.py, examples/credit_card.py, examples/hard_functions.py….
Installs other software
Following it will install packages (npm, pip, brew or similar). Those come from their own publishers, not from this skill.
How we know
The SKILL.md contains package-install commands.
Changes your AI's own settings, permissions or connectors
This weakens the protection between the skill and your computer, so later steps can happen without you being asked.
How we know
docs/index.html line 570 (and 1 more in that file): “cp ~/.claude/settings-kimi.json ~/.claude/settings.json”. Read 2026-10-04, commit 39e5f94.
docs/index.html, line 570 ↗11 smaller things worth knowing
Installs code straight from a web address, not a package registry; Changes your AI's own settings, permissions or connectors. Usually legitimate — listed so nothing is hidden.
How we know
Installs code straight from a web address, not a package registry — README.md line 92; Changes your AI's own settings, permissions or connectors — README.md line 318; Installs code straight from a web address, not a package registry — SKILL.md line 36; Installs code straight from a web address, not a package registry — docs/i18n/README_DE.md line 83; Changes your AI's own settings, permissions or connectors — docs/i18n/README_DE.md line 296; Installs code straight from a web address, not a package registry — docs/i18n/README_ES.md line 83. Read 2026-10-04, commit 39e5f94.
README.md, line 92 ↗README.md, line 318 ↗SKILL.md, line 36 ↗docs/i18n/README_DE.md, line 83 ↗docs/i18n/README_DE.md, line 296 ↗docs/i18n/README_ES.md, line 83 ↗Recently maintained
Its repository has had changes recently.
How we know
Last push to Optim-Agent/optim-agent: 2026-08-14 (51 days before the scan).
Read automatically from the skill’s own files on GitHub on 4 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Partly. Upload it in Claude’s settings — the instructions work; the scripts need the full folder.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
This skill ships 31 scripts beside its instructions. The download here is the SKILL.md alone — enough for the instructions, not for the parts that run code. Use the command route, or take the full folder from the repository.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end