agent-capability-assessor

agent-capability-assessor is a skill for Claude Code, Codex from majiayu000/claude-skill-registry. It costs 57 tokens per session (1,604 once invoked), scanned A, original, MIT.

An assessor that reviews an existing agent's description, skills, and workflow against a proposed task.

In plain words
What is it for?
Use it to compare agent capabilities with task requirements and identify strengths, gaps, and fit.
Why use it?
It helps determine whether an existing agent is suitable or whether a new one is needed.

Skill for Claude CodeCodex

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

Good fit Use it to compare agent capabilities with task requirements and identify strengths, gaps, and fit.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/majiayu000/claude-skill-registry/agent-capability-assessor
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-capability-assessor
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-capability-assessor

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-capability-assessor"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-capability-assessor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,604 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 $0.00057 $0.01604
Opus 5 $0.00028 $0.00802
Sonnet 5 $0.00011 $0.00321
Haiku 4.5 $0.00006 $0.00160

Measured 9d ago against content hash e62ba2906a5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-capability-assessor 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 9d 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-capability-assessor/SKILL.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Capability Assessor Skill

Instructions

  1. Review the agent file(s) to understand capabilities
  2. Analyze agent description, skills, and workflow
  3. Compare agent capabilities to task requirements
  4. Determine if agent can handle the task effectively
  5. Identify capability gaps or strengths
  6. Recommend whether to use existing agent or create new one
  7. Provide capability assessment report

Assessment Process

Step 1: Read Agent File

  • Read the agent's markdown file from .cursor/agents/
  • Understand agent's name, description, and purpose
  • Review agent's core principles and workflow
  • Note agent's available skills and capabilities

Step 2: Analyze Capabilities

  • Extract key capabilities from agent description
  • Identify what types of tasks the agent handles
  • Note any limitations or constraints
  • Understand agent's workflow and process

Step 3: Compare to Task Requirements

  • Review task description and requirements
  • Identify required capabilities for the task
  • Match task requirements to agent capabilities
  • Note any gaps or mismatches

Step 4: Make Assessment

  • Determine if agent can handle task (Yes/No/Partial)
  • Assess quality of match (Excellent/Good/Fair/Poor)
  • Identify capability gaps
  • Recommend action (Use existing / Create new / Enhance existing)

Capability Assessment Criteria

Excellent Match

  • Agent's primary purpose aligns with task
  • Agent has all required skills
  • Agent's workflow fits task requirements
  • No significant gaps

Good Match

  • Agent can handle task with minor adjustments
  • Agent has most required skills
  • Agent's workflow mostly fits
  • Minor gaps that can be worked around

Fair Match

  • Agent can handle task but not ideal
  • Agent has some required skills
  • Agent's workflow partially fits
  • Some gaps that may impact effectiveness

Poor Match

  • Agent is not well-suited for task
  • Agent lacks key required skills
  • Agent's workflow doesn't fit
  • Significant gaps that impact effectiveness

No Match

  • Agent cannot handle task
  • Agent lacks required capabilities
  • Task is outside agent's domain

Read the full file on GitHub · 264 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. 9d ago First seen · 264 lines · 57 tokens per session scan A e62ba2906a5b

Subscribe to this mod's changes

agent-capability-assessor is a skill published in the GitHub repository majiayu000/claude-skill-registry (606 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,604 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 2026-09-03.