intent-agent

A requirements-analysis tool that turns information from text, documents, conversations, issues, emails, and diagrams into structured software requirements. It can express those requirements as user stories, use cases, and domain models.

In plain words
What is it for?
Use it to gather requirements, define user stories with acceptance criteria, model use cases and business entities, detect ambiguity, and identify risks and assumptions.
Why use it?
It helps resolve unclear or incomplete requirements before design and coding begin. It also records assumptions, risks, actors, processes, and relationships that might otherwise be missed.

Agent

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 agents/itdojp/ae-framework/intent-agent
Clone the repo
git clone --depth 1 https://github.com/itdojp/ae-framework
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,717 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 $0.00000 $0.05717
Opus 5 $0.00000 $0.02858
Sonnet 5 $0.00000 $0.01143
Haiku 4.5 $0.00000 $0.00572

Measured yesterday against content hash 326b87f461e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

intent-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 yesterday.

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.

docs/legacy/agents/intent-agent.md · 813 lines

How it starts

The opening of the file, as written. The whole thing — 813 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intent Agent

🌍 Language / 言語: English | 日本語


English

The Intent Agent is a core component of the ae-framework Phase 1, responsible for requirements gathering, analysis, and intent extraction from multiple sources. It transforms raw requirements into structured formats that feed into subsequent phases of the architectural engineering process.

Overview

The Intent Agent handles the crucial first phase of ae-framework by:

  • Requirements Gathering: Collecting requirements from diverse sources including text, documents, conversations, issues, emails, and diagrams
  • Natural Language Processing: Extracting structured requirements from unstructured natural language
  • User Story Generation: Converting requirements into user stories with proper acceptance criteria
  • Use Case Creation: Building comprehensive use case models with actors, flows, and exceptions
  • Domain Modeling: Identifying entities, relationships, bounded contexts, and aggregates
  • Ambiguity Detection: Finding and suggesting resolutions for ambiguous requirements
  • Risk Analysis: Identifying potential risks and their mitigation strategies
  • Assumption Management: Tracking assumptions that need validation
  • Stakeholder Analysis: Analyzing stakeholder concerns and detecting conflicts
  • Traceability: Creating links between requirements and downstream artifacts
  • Specification Generation: Creating templates for Gherkin, OpenAPI, AsyncAPI, and GraphQL specifications

Architecture

Core Components

IntentAgent
├── Requirements Processing
│   ├── Source Extraction
│   ├── Natural Language Analysis
│   └── Requirement Categorization
├── Analysis & Modeling
│   ├── User Story Generation
│   ├── Use Case Creation
│   ├── Domain Model Building
│   └── Stakeholder Analysis
├── Quality Assurance
│   ├── Ambiguity Detection
│   ├── Completeness Validation
│   └── Risk Assessment
└── Output Generation
    ├── Specification Templates
    ├── Traceability Matrix
    └── Structured Reports

Read the full file on GitHub · 813 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. yesterday First seen · 813 lines · 0 tokens per session scan A 326b87f461e4

Subscribe to this mod's changes

intent-agent is an agent published in the GitHub repository itdojp/ae-framework (2 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 5,717 tokens. 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.

Related

Other agents, from other repositories

playwright-test-generator

Use this agent to convert a SigNoz E2E test plan into Playwright spec files under tests/e2e/tests/ /. Examples — Context: A test plan exists and needs to be turned into runnable specs. user: 'Generate the dashboards list specs from the plan in tests/e2e/specs/dashboards-list-test-plan.md' assistant: 'Using the…

SigNoz/signoz · 0 tokens

playwright-test-healer

Use this agent to debug and fix failing SigNoz E2E Playwright tests. Examples — Context: A spec is red. user: 'tests/e2e/tests/dashboards/list.spec.ts is failing, fix it' assistant: 'Using the healer agent to debug each failing scenario and adjust the spec.' Context: After a frontend change a previously-green spec…

SigNoz/signoz · 0 tokens

playwright-test-planner

Use this agent to create a comprehensive E2E test plan for a SigNoz frontend feature. Examples — Context: A new feature has shipped and we need test coverage. user: 'Plan E2E tests for the alerts list page' assistant: 'I'll use the planner agent to read the relevant frontend source, navigate the page in a real…

SigNoz/signoz · 0 tokens

codex

Production OpenAI-Codex-capable rootfs/initramfs.

the-void-ia/void-box · 0 tokens

claude

Production Claude-capable rootfs/initramfs.

the-void-ia/void-box · 0 tokens

doc-style

Markdown documentation prose — RFCs, ADRs, files under docs/, and READMEs — follows the same one-paragraph-per-line rule as commit messages. Write each paragraph on a single line; do not hard-wrap prose to a fixed column. The renderer reflows it to the reader's display width, whereas manual mid-paragraph line breaks…

the-void-ia/void-box · 0 tokens