refine-loop SKILL.md skillA
refine-loop from geiserx/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add geiserx/agent-skills/refine-loop@git:20260929.133011bPins git:20260929.133011b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- geiserx/agent-skills
- Path
codex/skills/refine-loop/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260929.133011b, committed Sep 29, 2026
- First version recorded
- Sep 29, 2026
- Size
- 18,763 bytes
- Repository stars
- 4
- License
- GPL-3.0
Runs a safe, resumable refinement loop over a working repository. It discovers behavior-preserving improvements through four evidence-based lenses, ranks them by ROI, applies one small change at a time, verifies independently, and stops deterministically at diminishing returns or a safety limit. Use when explicitly asked to run refine-loop on an existing project.
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
## Running in Codex This is the Codex copy of this skill. Read the rest of it with these translations: - Agents launched in parallel: spawn each one with `spawn_agent` before waiting on any, then collect the results with `wait_agent`. Tell every agent you spawn not to spawn agents of its own. If subagents are unavailable, run each lane yourself, one after another. - "Your default model" and "your strongest model": spawn the agent with an `agent_type` whose role file in `~/.codex/agents/` sets `model` and `model_reasoning_effort`. An agent without a role runs on the session's model. - A slash command such as `/name`: mention the skill as `$name`. - This repository's hooks and `.claude/` paths are for Claude Code only, and nothing here installs a Codex hook. A loop runs one pass per invocation, saves its state and reports how to resume. - `CLAUDE.md`: also read `AGENTS.md`, which is the file Codex loads. # refine-loop Refine a working repository through small changes that preserve observable behavior. The loop is not a feature, bug-fix, security-remediation, migration, or rewrite workflow. …
Read the whole file at its exact version.
How to install
mdr add geiserx/agent-skills/refine-loop@sha256:ab2ae4ad1e251229The line at the top of this page pins the label git:20260929.133011b, 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_v65zk7igb4ek5hzt)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Sep 29, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260929.133011b latest | 2026-09-29 | 133011b | 18,763 B | A | view · diff |
| git:20260929.bdaf144 | 2026-09-29 | bdaf144 | 18,732 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 (18763 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
geiserx/agent-skills · 4 stars · license GPL-3.0 · pushed 2026-10-14 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_v65zk7igb4ek5hzt GET https://markdownregistry.com/api/v1/resolve?ref=geiserx/agent-skills/refine-loop GET https://markdownregistry.com/api/v1/blob/ab2ae4ad1e25122900c3be8ca33872887467760664864c60d31f0d918afc3830
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.
More from geiserx/agent-skills
Every file in geiserx/agent-skills