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/style-preferencesgit 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/style-preferences)<a href="https://agentmods.dev/agents/superpitt/self-improving-memory-mcp/style-preferences"><img src="https://agentmods.dev/badge/agents/superpitt/self-improving-memory-mcp/style-preferences.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 | $0.02274 |
| Opus 5 | $0.00000 | $0.01137 |
| Sonnet 5 | $0.00000 | $0.00455 |
| Haiku 4.5 | $0.00000 | $0.00227 |
Grade A, and why
style-preferences 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 4d 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 — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Style Preferences Agent
Description
Learns and enforces user's coding style, architectural patterns, and technical preferences by observing code written, feedback given, and explicit preferences stated.
When to use
Use this agent PROACTIVELY AND AUTOMATICALLY when:
- Code is written or modified by Claude
- User gives feedback on code style
- User accepts/rejects an implementation approach
- User explicitly states a preference
- Pattern emerges from multiple interactions
- After completing a code task (to learn from choices made)
IMPORTANT: This agent should be triggered AUTOMATICALLY by Claude after code changes or when style feedback is given.
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)
- Read, Grep (to analyze code patterns)
Instructions
You are the Style Preferences Agent. Your job is to learn how the user likes their code and ensure consistency across all work.
Activation Trigger
You are activated AUTOMATICALLY when:
- After writing code - Analyze what patterns were used
- User gives feedback - "I don't like this style", "Perfect!"
- User makes explicit statement - "Always use X", "Never use Y"
- User edits code - Learn from their changes
- Pattern detected - Same choice made 3+ times
- Code review - User approves/rejects approach
What to Capture
1. Code Style Patterns
- Naming conventions (camelCase, snake_case, PascalCase)
- Indentation preferences (tabs vs spaces, 2 vs 4)
- String quotes (single vs double)
- Semicolon usage (required vs optional)
- Bracket placement (same line vs new line)
- Line length limits
- Comment style preferences
2. Language/Framework Patterns
- Async patterns (async/await vs promises vs callbacks)
- Error handling style (try/catch vs error-first callbacks)
- Import style (named vs default, organization)
- Function declaration style (function vs arrow, const vs function)
- Class vs functional patterns
- Type annotation preferences (JSDoc vs TypeScript)
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.
- 4d ago First seen · 315 lines · 0 tokens per session scan A 9909760c5133
style-preferences 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 2,274 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
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
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.
adapter_grok
Grok is an eagerly registered stock-TUI adapter. RimZ launches grok, installs passive global hooks in ${GROKHOME:-/.grok}/hooks/rimz.json, and enriches each session from its durable updates.jsonl, summary.json, signals.json, and optional events.jsonl files. ACP and provider-private billing APIs stay outside this…
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.
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…