agentmods.dev

agents-refine

agents-refine is a skill for Claude Code, Codex from spideynolove/claude-dotfiles. It costs 45 tokens per session (1,864 once invoked), scanned A, original, MIT.

A command that improves AGENTS.md instruction files through repeated reviews by different AI models. AGENTS.md files contain project rules for coding agents, and the command supports shared root rules and project-specific rules.

In plain words
What is it for?
Use it to evaluate and revise root or project AGENTS.md files, run several refinement rounds, start from a baseline, or preview changes without writing them.
Why use it?
It helps turn vague or incomplete agent instructions into clearer rules with fewer gaps and contradictions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions AGENTS.md; mentions Codex.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is ROOT_AGENTS=$(find ../.. -maxdepth 2 -name "AGENTS.md" | head -1).

not rated 2repo 3mo ago A scan 45 tokens original MIT

Good fit Use it to evaluate and revise root or project AGENTS.md files, run several refinement rounds, start from a baseline, or preview changes without writing them.

Compare 6 skills from other repositories ↓
View source ↗ spideynolove/claude-dotfiles
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/spideynolove/claude-dotfiles
agentmods
npx agentmods add skills/spideynolove/claude-dotfiles/agents-refine

Made for: Claude Code, Codex.

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 agents-refine

README.md
[![agentmods](https://agentmods.dev/badge/skills/spideynolove/claude-dotfiles/agents-refine/github.svg)](https://agentmods.dev/skills/spideynolove/claude-dotfiles/agents-refine)
Your own site
<a href="https://agentmods.dev/skills/spideynolove/claude-dotfiles/agents-refine"><img src="https://agentmods.dev/badge/skills/spideynolove/claude-dotfiles/agents-refine/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agents-refine

Your own site · 80×15
<a href="https://agentmods.dev/skills/spideynolove/claude-dotfiles/agents-refine"><img src="https://agentmods.dev/badge/skills/spideynolove/claude-dotfiles/agents-refine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,864 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 original 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 $0.00045 $0.01864
Opus 5 $0.00023 $0.00932
Sonnet 5 $0.00009 $0.00373
Haiku 4.5 $0.00005 $0.00186

Measured 10d ago against content hash 2a5a47486213, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agents-refine 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 10d 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.

.claude-global-backup/skills/agents-refine/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/agents-refine

Refine AGENTS.md files through a multi-model evaluation loop: Claude (Opus) → Codex → Claude final pass. Produces HLD (root) and LLD (project-specific) rules with measurable improvement each cycle.

Usage

/agents-refine                        # refine AGENTS.md in current directory (auto-detect root vs project)
/agents-refine root                   # explicitly refine root/HLD AGENTS.md
/agents-refine project [path]         # refine project-level LLD AGENTS.md, links to root
/agents-refine --rounds N             # run N full cycles (default: 3)
/agents-refine --bootstrap            # start from Karpathy baseline if no AGENTS.md exists
/agents-refine --dry-run              # show evaluation output without writing

What this skill does

Runs a structured refinement loop that mirrors your manual process:

  1. Opus evaluates — subagent reads AGENTS.md, scores it on 6 axes (completeness, precision, enforceability, anti-pattern coverage, tech fit, LLD/HLD coherence), outputs a critique with specific gaps
  2. Patch v_n → v_n+1 — applies critique: tighten vague rules, cut redundancies, add missing constraints
  3. Codex evaluates independently — runs codex CLI with a reviewer persona, no access to the Opus critique (independent signal)
  4. Patch v_n+1 → v_n+2 — applies Codex findings
  5. Opus final polish — coherence pass: removes contradictions, normalizes format, checks HLD↔LLD alignment
  6. Write final — overwrites AGENTS.md, prints a diff summary

Execution protocol

Step 0 — Detect context

# Determine mode
if [ -f AGENTS.md ]; then MODE="refine"; else MODE="bootstrap"; fi
# Detect if root (no parent AGENTS.md within 3 levels) or project
ROOT_AGENTS=$(find ../.. -maxdepth 2 -name "AGENTS.md" | head -1)
  • If ROOT_AGENTS is empty → this is root/HLD mode
  • If ROOT_AGENTS exists → this is project/LLD mode; read it first

Step 1 — Read and version current AGENTS.md

Read the current AGENTS.md (or bootstrap from Karpathy baseline below if --bootstrap flag). Store as VERSION_0.

Read the full file on GitHub · 189 lines

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. 10d ago First seen · 189 lines · 45 tokens per session scan A 2a5a47486213

Subscribe to this mod's changes

agents-refine is a skill published in the GitHub repository spideynolove/claude-dotfiles (2 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 1,864 once invoked, about $0.0002 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.

Building agents
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens