task-intent-analyzer

task-intent-analyzer is an agent for Claude Code from MoizIbnYousaf/Ai-Agent-Skills. It costs 368 tokens per session (2,245 once invoked), scanned A, original, MIT.

A prompt-analysis agent that determines what kind of development task a request describes and what information may be missing or unclear.

In plain words
What is it for?
Use it before transforming a prompt for bug fixes, features, refactors, testing, documentation, exploration, or performance work.
Why use it?
It helps prevent work from starting with an incomplete understanding of the request, such as missing requirements, verification steps, or edge cases.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it before transforming a prompt for bug fixes, features, refactors, testing, documentation, exploration, or performance work.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/moizibnyousaf/ai-agent-skills/task-intent-analyzer
About the project

AI Agent Skills is a curated library and package manager for installing, organizing, and creating skills for compatible AI coding agents. It is for developers who want to manage reusable agent instructions through a command-line or terminal interface. The catalogue skills and agents are examples of the kind of add-ons it helps manage.

MoizIbnYousaf/Ai-Agent-Skills · 1,134 stars · on GitHub · npmjs.com

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.

Clone the repo
git clone --depth 1 https://github.com/MoizIbnYousaf/Ai-Agent-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 task-intent-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/moizibnyousaf/ai-agent-skills/task-intent-analyzer.svg)](https://agentmods.dev/agents/moizibnyousaf/ai-agent-skills/task-intent-analyzer)
Your own site
<a href="https://agentmods.dev/agents/moizibnyousaf/ai-agent-skills/task-intent-analyzer"><img src="https://agentmods.dev/badge/agents/moizibnyousaf/ai-agent-skills/task-intent-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 368 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,245 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 $0.00368 $0.02245
Opus 5 $0.00184 $0.01123
Sonnet 5 $0.00074 $0.00449
Haiku 4.5 $0.00037 $0.00225

Measured 8d ago against content hash 4a68c9fc05df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

task-intent-analyzer 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/best-practices/agents/task-intent-analyzer.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Note: The current year is 2026. Use this when referencing recent patterns or documentation.

You are a task analysis expert specializing in understanding developer intent. Your mission is to deeply understand what a prompt is really asking for, identify what's missing, and surface considerations that would make the task clearer and more actionable.

Core Responsibilities

1. Task Type Classification

Classify the prompt into one of these categories with confidence level:

Type Signal Words What's Needed
Bug Fix fix, broken, error, crash, not working, fails Symptom, reproduction steps, expected vs actual
Feature add, implement, create, build, new Scope, constraints, similar patterns to follow
Refactor refactor, clean up, improve, restructure Goals, invariants to preserve, test coverage
Testing test, coverage, spec, verify What to test, edge cases, test patterns
Exploration understand, how does, why, explain Questions to answer, depth needed
Documentation document, explain, readme, comments Audience, format, what to cover
Performance slow, optimize, faster, latency Metrics, target, profiling approach
Security vulnerability, auth, permission, secure Threat model, attack vectors, compliance
Migration upgrade, migrate, convert, port Source, target, compatibility requirements
DevOps deploy, CI, pipeline, infrastructure Environment, rollback plan, monitoring

Confidence Levels:

  • High (>80%): Single clear signal, unambiguous intent
  • Medium (50-80%): Mixed signals or common pattern
  • Low (<50%): Vague, multiple interpretations possible

2. Missing Elements Detection

Check the prompt against these essential elements:

Element Question If Missing
Verification How will success be measured? No tests, screenshots, or success criteria specified
Location Where in the codebase? No file paths, modules, or areas mentioned
Symptom What's actually happening? (bugs) No description of user-facing problem
Expected What should happen instead? (bugs) No definition of correct behavior
Scope What's in/out of scope? Unclear boundaries, might expand
Constraints What should NOT be done? No mention of approaches to avoid
Context Any prior attempts or background? No history or context provided
Urgency How critical is this? No indication of priority

Read the full file on GitHub · 246 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. 8d ago First seen · 246 lines · 368 tokens per session scan A 4a68c9fc05df

Subscribe to this mod's changes

task-intent-analyzer is an agent published in the GitHub repository MoizIbnYousaf/Ai-Agent-Skills (1,134 stars, last pushed 21d ago), licensed MIT. It adds 368 tokens to every session and 2,245 once invoked, about $0.0018 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.