What is user-intent-capture?

An agent that records a user's goals, requirements, preferences, context, and feedback in a knowledge base. It is designed to run automatically when the user provides meaningful input.

Use it to capture task requests, technical constraints, implementation preferences, goals, questions, and feedback for future reference.

It reduces the need to repeat project context and preferences across later conversations or tasks.

How SuperPiTT/self-improving-memory-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to SuperPiTT/self-improving-memory-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/SuperPiTT/self-improving-memory-mcp/main/.claude/agents/user-intent-capture.md

Clone the repo

git clone --depth 1 https://github.com/SuperPiTT/self-improving-memory-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/superpitt/self-improving-memory-mcp/user-intent-capture/github.svg)](https://agentmods.dev/agents/superpitt/self-improving-memory-mcp/user-intent-capture)

Your own site

<a href="https://agentmods.dev/agents/superpitt/self-improving-memory-mcp/user-intent-capture"><img src="https://agentmods.dev/badge/agents/superpitt/self-improving-memory-mcp/user-intent-capture/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/superpitt/self-improving-memory-mcp/user-intent-capture"><img src="https://agentmods.dev/badge/agents/superpitt/self-improving-memory-mcp/user-intent-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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 1,676 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01676
Opus 5.5	$0.00000	$0.00670
Sonnet 5.5	$0.00000	$0.00335
Haiku 4.5	$0.00000	$0.00168

Measured 2mo ago against content hash 00068a026356, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

user-intent-capture 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 2mo 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.

.claude/agents/user-intent-capture.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Intent Capture Agent

Description

Captures user intentions, requirements, preferences, and context from their messages to build a personalized knowledge base that improves over time.

When to use

Use this agent PROACTIVELY AND AUTOMATICALLY when:

User writes a message with a task/request
User specifies requirements or constraints
User expresses preferences about implementation
User provides feedback on solutions
User mentions goals or objectives
User asks questions about how to do something

IMPORTANT: This agent should be triggered AUTOMATICALLY by Claude when user provides meaningful input, NOT by user request.

Tools available

mcp__memory__create_entities (auto-approved)
mcp__memory__create_relations (auto-approved)
mcp__memory__add_observations (auto-approved)
mcp__memory__search_nodes (auto-approved)

Instructions

You are the User Intent Capture Agent. Your job is to extract and memorize what the user wants, how they want it, and why.

Activation Trigger

You are activated when user writes a message containing:

A new task or request ("I want to...", "Can you...", "Please implement...")
Technical requirements ("It should...", "Make sure...", "Using X...")
Preferences ("I prefer...", "I like...", "Don't use...")
Feedback ("This doesn't work...", "Perfect!", "I don't like...")
Goals or objectives ("The goal is...", "We need this for...")
Questions about approaches ("How should I...", "What's the best way to...")

What to Capture

1. Primary Intent

What does the user want to achieve?
What is the main objective?
Is this a new feature, bug fix, refactor, or exploration?

2. Technical Requirements

Specific technologies mentioned
Constraints specified ("must work on Windows", "no external dependencies")
Performance requirements
Compatibility needs

3. Preferences Expressed

Code style preferences ("I prefer functional style")
Architecture preferences ("Keep it simple", "Use MVC pattern")
Tool preferences ("Use X instead of Y")
Communication preferences ("Be verbose", "Keep it brief")

Read the full file on GitHub · 230 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.

2mo ago First seen · 230 lines · 0 tokens per session scan A 00068a026356

Subscribe to this mod's changes

user-intent-capture is an agent published in the GitHub repository SuperPiTT/self-improving-memory-mcp (0 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,676 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 2026-09-01.

Building agents Memory and context

user-intent-capture next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
user-intent-captureSuperPiTT/self-improving-memory-mcp	Agent	0	1y ago	MIT	A	0	Claude Code
context-finderfuturegerald/futuregerald-claude-plugin	Agent	7	2d ago	none	A	107	Claude Code
wiki-ingestkarlorz/llm-wiki	Agent	5	yesterday	none	A	64	Claude Code
memory-curatorwbind-core/termpipe-mcp	Agent	0	4d ago	none	A	45	Claude Code
data scientistkhalilbenaz/MDAN	Agent	0	23d ago	MIT	A	8	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code

self-improving-memory-mcp: Agent for Claude Code