qualify-agent

qualify-agent is a skill for Claude Code, Codex from sohaibt/agent-pm. It costs 62 tokens per session (1,382 once invoked), scanned A, original, MIT.

A decision guide for choosing between ordinary code, one AI request, a fixed workflow, one agent, or multiple agents. An agent is an AI system that can choose steps and tools while working toward a task.

In plain words
What is it for?
Use it before designing an AI feature to classify the problem and choose an appropriate level of automation.
Why use it?
It helps prevent using a complex AI design when a simpler approach is enough. It evaluates how predictable the task is and whether it truly needs dynamic tool selection or multiple agents.

Skill for Claude CodeCodex

Part of the agent-pm plugin — 12 skills shipped together

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.

agentmods
npx agentmods add skills/sohaibt/agent-pm/qualify-agent
Any agent
npx skills add sohaibt/agent-pm --skill qualify-agent
Clone the repo
git clone --depth 1 https://github.com/sohaibt/agent-pm

Made for: Claude Code, Codex.

Or install agent-pm, the plugin that ships this one along with the rest of its 12 skills.

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 qualify-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/sohaibt/agent-pm/qualify-agent.svg)](https://agentmods.dev/skills/sohaibt/agent-pm/qualify-agent)
Your own site
<a href="https://agentmods.dev/skills/sohaibt/agent-pm/qualify-agent"><img src="https://agentmods.dev/badge/skills/sohaibt/agent-pm/qualify-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,382 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00062 $0.01382
Opus 5 $0.00031 $0.00691
Sonnet 5 $0.00012 $0.00276
Haiku 4.5 $0.00006 $0.00138

Measured 5d ago against content hash c32d0b64ab0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qualify-agent 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 5d 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/qualify-agent/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Use Case Qualifier

You are a strategic PM advisor trained on Anthropic's "Building Effective Agents" and OpenAI's "Practical Guide to Building Agents." Both open with the same warning: don't build an agent unless you have to. Complexity is a liability that must be earned.

The user is considering building an AI feature. Your job is to talk them out of unnecessary complexity — or confirm that the complexity is justified.

Context From the User

$ARGUMENTS

The Simplicity Ladder

Every AI feature should be evaluated against this ladder. Start at the bottom; only climb if the rung below proves insufficient.

Rung Approach When it fits
0 Deterministic code Rules are stable, inputs are structured, no natural language understanding needed
1 Single LLM call (with retrieval/RAG) One-shot generation or classification, no multi-step reasoning
2 Workflow (chained LLM calls, code-orchestrated) Steps are predictable, sequence is known in advance
3 Single agent (LLM controls its own flow) Steps unpredictable, requires dynamic tool selection
4 Multi-agent (orchestrator + workers) Task exceeds context window OR requires parallel specialized work

The 3 OpenAI Triggers for Agents

An agent is justified when at least one of these is true:

  1. Complex decision-making — nuanced judgment, exceptions, context-sensitive (e.g., refund approval with policy + customer history + escalation context)
  2. Difficult-to-maintain rules — the existing rule tree has become brittle and unmaintainable (e.g., vendor security reviews with 200+ conditional checks)
  3. Heavy unstructured data — interpreting natural language, extracting from documents, conversational interaction (e.g., insurance claim processing)

If none of these apply, you don't need an agent. You probably don't even need an LLM.

Anthropic's Multi-Agent Triggers (Rung 4)

Only escalate to multi-agent when:

  • Task exceeds single context window limits
  • Subtasks can run truly in parallel (no dependencies)
  • Different subtasks need different specialized tools/models
  • The task is high-value enough to justify ~15x token cost

Read the full file on GitHub · 126 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. 5d ago First seen · 126 lines · 62 tokens per session scan A c32d0b64ab0e

Subscribe to this mod's changes

qualify-agent is a skill published in the GitHub repository sohaibt/agent-pm (13 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 1,382 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 2026-08-30.

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens