run-optimizer SKILL.md skillA
run-optimizer from skillberry-ai/cap-evolve is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add skillberry-ai/cap-evolve/run-optimizer@git:20260822.5dbe47fPins git:20260822.5dbe47f in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- skillberry-ai/cap-evolve
- Path
skills/optimizers/run-optimizer/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260822.5dbe47f, committed Aug 22, 2026
- First version recorded
- Jun 17, 2026
- Size
- 5,944 bytes
- Repository stars
- 66
- License
- Apache-2.0
Drives any shell-invokable coding agent (Claude Code, Codex, Gemini CLI, opencode, Cursor, Factory Droid, GitHub Copilot CLI, Kimi, Pi, Antigravity, OpenClaw, IBM Bob, or a fully custom command) as the edit proposer in a cap-evolve run, resolving the named optimizer from optimizers/registry.yaml. Use this as the optimizer for every run; pick the concrete agent with --name (or optimizer_skill in the spec). Use --name mock for a deterministic, zero-API proposer in tests and CI.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# run-optimizer — one runner, a registry of agents An *optimizer* is the agent that reads the current capability + the failure diagnosis and proposes an edit. Every such agent follows the same contract: given a working directory (a copy of the parent candidate) and an `INSTRUCTIONS.md`, edit the files in place. Because the contract is identical, one runner serves them all — the only thing that varies per agent is the shell command, which lives as a row in `optimizers/registry.yaml`. Adding an optimizer is **one YAML row**, not a new skill directory. ## How it works 1. The loop calls `run.py --name <optimizer> --workdir <copy> --prompt INSTRUCTIONS.md`. 2. The runner reads the registry, resolves the row, and expands its `command_template` (placeholders below) into argv. 3. It runs that command with `cwd = workdir`, so the agent edits the candidate files directly. Output is summarized as JSON (`returncode`, `auth_present`, `stdout_tail`). 4. Streams: **stdout is exactly one JSON object**; the agent CLI's **stderr is relayed** to the runner's stderr on success as well as failure, so a CLI that prints a diagnostic and exits 0 is not silently successful. …
Read the whole file at its exact version.
How to install
mdr add skillberry-ai/cap-evolve/run-optimizer@sha256:9545f46b0f73f0f3The line at the top of this page pins the label git:20260822.5dbe47f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_cu7o67blbjh665zt)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jun 17, 2026 and Aug 22, 2026, about one every 17 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260822.5dbe47f latest | 2026-08-22 | 5dbe47f | 5,944 B | A | view · diff |
| git:20260624.1251701 | 2026-06-24 | 1251701 | 5,478 B | A | view · diff |
| git:20260617.7ae99d3 | 2026-06-17 | 7ae99d3 | 4,981 B | A | view · diff |
| git:20260617.4c87ed1 | 2026-06-17 | 4c87ed1 | 5,215 B | A | view · diff |
| git:20260617.92b5c65 | 2026-06-17 | 92b5c65 | 3,321 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5944 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
skillberry-ai/cap-evolve · 66 stars · license Apache-2.0 · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_cu7o67blbjh665zt GET https://markdownregistry.com/api/v1/resolve?ref=skillberry-ai/cap-evolve/run-optimizer GET https://markdownregistry.com/api/v1/blob/9545f46b0f73f0f3e95ae891a382f4ae1f5cb13769e9848682035cc4af404c47
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.