agent-curator

agent-curator is a skill for Claude Code, Codex from majiayu000/claude-skill-registry. It costs 39 tokens per session (3,761 once invoked), scanned A, original, MIT.

A guided process for improving one AI agent through a structured conversation. It covers the agent’s knowledge, behaviour, tools, local reference material, and instructions.

In plain words
What is it for?
Use it to refine an agent for general use or prepare one for a specific project, including its role, knowledge sources, and tool setup.
Why use it?
It provides a systematic way to find weaknesses in an agent definition instead of changing prompts or tools without a clear review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to refine an agent for general use or prepare one for a specific project, including its role, knowledge sources, and tool setup.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/majiayu000/claude-skill-registry/agent-curator
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 majiayu000/claude-skill-registry --skill agent-curator
Clone the repo
git clone --depth 1 https://github.com/majiayu000/claude-skill-registry

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 agent-curator

README.md
[![agentmods](https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-curator/github.svg)](https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-curator)
Your own site
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-curator"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-curator/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 agent-curator

Your own site · 80×15
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-curator"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,761 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00039 $0.03761
Opus 5 $0.00019 $0.01880
Sonnet 5 $0.00008 $0.00752
Haiku 4.5 $0.00004 $0.00376

Measured 8d ago against content hash d84a9723d39c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agent-curator 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 8d 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.

skills/agent/agent-curator/SKILL.md · 406 lines

How it starts

The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Curator Skill

Activation

Invoke for ad-hoc agent curation or project preparation:

[ACTIVATE:AGENT_CURATOR_V1]
Parameters:
  agent: path/to/agent.md
  mode: broad | project
  project: {project-name}  # Required if mode=project

Purpose

Drive a structured conversation to deeply improve an agent definition across all dimensions:

  1. Knowledge Sources (P0) — Find and integrate esteemed references
  2. Persona & Doctrine (P1) — Sharpen identity and mental model
  3. Tooling & MCP (P2) — Optimize tool and server configuration
  4. Local Corpora (P3) — Materialize high-value knowledge locally
  5. Instruction Quality (P4) — Refine priorities, modes, and behaviors

Two Modes

Broad Improvement Mode

For general agent enhancement:

  • Changes should improve effectiveness across all use cases
  • Improvements are candidates for upstream contribution
  • Long-term maintenance burden considered

Project-Specific Mode

For preparing an agent for a specific project:

  • Changes may include project-specific knowledge/tooling
  • Consider whether changes should stay local or go upstream
  • Immediate utility prioritized, but long-term impact considered

Execution Flow

Phase 0: Scope Establishment

Present scope selection:

╔═══════════════════════════════════════════════════════════════════════╗
║                    AGENT CURATION SESSION                             ║
╠═══════════════════════════════════════════════════════════════════════╣
║                                                                        ║
║  Agent: {agent-name}                                                   ║
║  Tier: {focused | expert | phd}                                        ║
║  Current File: {path}                                                  ║
║                                                                        ║
║  What is the goal of this curation session?                           ║
║                                                                        ║
║  [B] Broad Improvement                                                 ║
║      Enhance general effectiveness across all use cases               ║
║      Changes are candidates for upstream contribution                  ║
║                                                                        ║
║  [P] Project-Specific Preparation                                      ║
║      Optimize for: {project-name if provided}                         ║
║      May include project-specific knowledge/tooling                    ║
║                                                                        ║
╚═══════════════════════════════════════════════════════════════════════╝

Read the full file on GitHub · 406 lines

Files

What ships with it

1 file 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. 8d ago First seen · 406 lines · 39 tokens per session scan A d84a9723d39c

Subscribe to this mod's changes

agent-curator is a skill published in the GitHub repository majiayu000/claude-skill-registry (600 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 3,761 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 2026-09-03.