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.
npx agentmods add agents/superpitt/self-improving-memory-mcp/user-intent-capturegit clone --depth 1 https://github.com/SuperPiTT/self-improving-memory-mcpWrote 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.
[](https://agentmods.dev/agents/superpitt/self-improving-memory-mcp/user-intent-capture)<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="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.01676 |
| Opus 5 | $0.00000 | $0.00838 |
| Sonnet 5 | $0.00000 | $0.00335 |
| Haiku 4.5 | $0.00000 | $0.00168 |
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 3d 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.
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")
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.
- 3d ago First seen · 230 lines · 0 tokens per session scan A 00068a026356
user-intent-capture is an agent published in the GitHub repository SuperPiTT/self-improving-memory-mcp (0 stars, last pushed 11mo 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.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
portable-memory-parent-orchestrator
Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…
context
Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.
neon-drizzle-expert
Expert in Neon PostgreSQL (v17), Drizzle ORM (v0.44.4), and Zod (v4.0.17) schema validation for production memory systems. Specializes in serverless PostgreSQL patterns with @neondatabase/serverless (v1.0.1), type-safe database operations, and migration strategies.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.