refine-loop

refine-loop is a skill for Claude Code from GeiserX/claude-code-parallel-skills. It costs 70 tokens per session (3,978 once invoked), scanned A, original, GPL-3.0.

A repeatable process for finding and applying small improvements to a code repository while preserving its existing behavior. A repository is the project folder containing its code and history.

In plain words
What is it for?
Use it to inspect a repository from several evidence-based angles, rank possible improvements, apply them one at a time, and verify each result independently.
Why use it?
It turns broad cleanup into small, checked changes that can be resumed safely. It stops when further changes offer little benefit or reach a safety limit.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to inspect a repository from several evidence-based angles, rank possible…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/geiserx/claude-code-parallel-skills/refine-loop
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.

Any agent
npx skills add GeiserX/claude-code-parallel-skills --skill refine-loop
Clone the repo
git clone --depth 1 https://github.com/GeiserX/claude-code-parallel-skills

Made for: Claude Code.

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 refine-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/geiserx/claude-code-parallel-skills/refine-loop.svg)](https://agentmods.dev/skills/geiserx/claude-code-parallel-skills/refine-loop)
Your own site
<a href="https://agentmods.dev/skills/geiserx/claude-code-parallel-skills/refine-loop"><img src="https://agentmods.dev/badge/skills/geiserx/claude-code-parallel-skills/refine-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,978 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.
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 $0.00070 $0.03978
Opus 5 $0.00035 $0.01989
Sonnet 5 $0.00014 $0.00796
Haiku 4.5 $0.00007 $0.00398

Measured 6d ago against content hash a9878f9d10bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

refine-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 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.

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.

loops/refine-loop/SKILL.md · 310 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Files

What ships with it

4 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. 6d ago First seen · 310 lines · 70 tokens per session scan A a9878f9d10bf

Subscribe to this mod's changes

refine-loop is a skill published in the GitHub repository GeiserX/claude-code-parallel-skills (2 stars, last pushed 23d ago), licensed GPL-3.0. It adds 70 tokens to every session and 3,978 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

code-craft

Professional code craftsmanship standards, especially how to write comments the right way. Use whenever writing or editing code, when adding comments or docstrings, during code review, or when the user asks for clean, production-quality, well-documented code. Covers comment discipline (explain why not what)…

Ohswedd/praxis · 90 tokens

audit-evidence

What an auditor is allowed to assert, and what it must cite. Preloaded into every praxis review auditor through the skills frontmatter field, so the rule exists once. Use whenever you are reviewing, auditing, or verifying a change and about to state a verdict: it defines the difference between a finding and a guess…

Ohswedd/praxis · 95 tokens

review-scope

What 'the change' means in a review, and how an auditor establishes it: the branch's commits since its base as well as what is still uncommitted, never the working tree alone. Preloaded into every praxis review auditor through the skills frontmatter field, so the rule exists once. Use whenever you are about to audit…

Ohswedd/praxis · 85 tokens

g-review

Run the review gate on the current branch diff. Runs the test suite, captures the diff, and dispatches code-lead, which verifies done conditions and reviews the diff itself. Issues MERGE READY or HOLD.

onlygian/G-Forge · 46 tokens

g-audit

Full-codebase or targeted code quality audit. Detects SOLID violations, code smells, architectural drift, dead code, and test coverage gaps. Targeted scope produces an inline report. Whole-codebase scope produces a prioritised roadmap milestone.

onlygian/G-Forge · 52 tokens

g-refactor

Guided refactor workflow — identify target, pre-analyse, spec, approve, execute, review. Accepts a scope path, an audit milestone file, or runs interactively. Safe-by-default: checks test coverage before execution and runs the full review gate after.

onlygian/G-Forge · 0 tokens