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 skills add VersoXBT/claude-initial-setup --skill memory-patternsgit clone --depth 1 https://github.com/VersoXBT/claude-initial-setupWrote 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/skills/versoxbt/claude-initial-setup/memory-patterns)<a href="https://agentmods.dev/skills/versoxbt/claude-initial-setup/memory-patterns"><img src="https://agentmods.dev/badge/skills/versoxbt/claude-initial-setup/memory-patterns.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 5.1 | $0.00049 | $0.01269 |
| Opus 5 | $0.00024 | $0.00634 |
| Sonnet 5 | $0.00010 | $0.00254 |
| Haiku 4.5 | $0.00005 | $0.00127 |
Grade A, and why
memory-patterns 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Patterns
Claude Code's auto memory system persists knowledge across sessions via files in the memory directory. MEMORY.md is always loaded into context; topic files store detailed notes referenced from MEMORY.md.
When to Use
- User asks "remember this" or "always do X"
- User corrects a mistake that came from memory — update the source
- You discover stable project patterns worth persisting
- User asks about organizing cross-session knowledge
- You need to structure MEMORY.md or create topic files
Core Patterns
MEMORY.md Structure
MEMORY.md is the index file — always loaded, so it must stay concise (under 200 lines). Use it as a table of contents pointing to detailed topic files:
# Project Memory
## Project Overview
- Name: acme-api
- Stack: Node.js, Express, PostgreSQL, TypeScript
- Test framework: Vitest
- Package manager: pnpm
## Key Conventions
- Use Zod for all input validation
- Repository pattern for database access
- All API responses follow ApiResponse<T> interface
- Feature branches: feat/description, fix/description
## Architecture
- See [architecture.md](./architecture.md) for service layout
- See [database.md](./database.md) for schema notes
## User Preferences
- Prefers functional style over classes
- Always use named exports (no default exports)
- Run tests before committing
## Known Issues
- See [debugging.md](./debugging.md) for recurring problems
Topic File Organization
Create separate files for detailed knowledge. Link them from MEMORY.md:
memory/
MEMORY.md # Index (always loaded, < 200 lines)
architecture.md # Service layout, module boundaries
database.md # Schema notes, migration patterns
debugging.md # Recurring issues and solutions
patterns.md # Code patterns specific to this project
api-conventions.md # API design decisions
Each topic file should be self-contained:
# Architecture Notes
## Service Layout
- src/services/ — Business logic, one file per domain
- src/routes/ — Express route handlers, thin layer
- src/db/ — Database access via repository pattern
- src/middleware/ — Auth, validation, error handling
## Module Boundaries
- Services never import from routes
- Routes call services, never DB directly
- Middleware is stateless
## Key Dependencies
- src/services/auth.ts depends on src/db/users.ts
- src/services/billing.ts depends on external Stripe SDK
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 · 176 lines · 49 tokens per session scan A 8a887aee3bea
memory-patterns is a skill published in the GitHub repository VersoXBT/claude-initial-setup (4 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 1,269 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
learner
Post-debugging knowledge extraction — captures non-obvious, codebase-specific learnings that pass quality gates. Invoke after resolving tricky bugs or discovering surprising behavior.
capture-learnings
Use in the Learn phase at the end of every task, before declaring done - dispatches the learner agent to record what was learned (conventions, pitfalls, reuse points, decisions) to the cross-session store and refresh the committed memory index, then closes the phase. Runs inline on the main thread (it owns the state…
claudehut-init
Use once per project before starting work (or when ClaudeHut reports no codebase index) to bootstrap ClaudeHut for a Java/Spring repository - detects the stack, generates the project memory + index + path-scoped rules, and wires the always-load @import slice. Invoked as /claudehut:claudehut-init. Idempotent.
summer-kb-setup
Install or refresh a service-scoped Summer Framework (io.f8a.summer) knowledge base in the current consumer service's .claude/summer-kb/. Use when a service that depends on Summer needs its local KB, when onboarding a new ewallet service, when asked to "set up / install / refresh the Summer KB", or when Summer was…
agents-skills-feedback-loop
Adds per-skill learnings loops for dated patterns, mistakes, and domain facts. Use when wiring skill memory, consolidation, or drift audits.
dev-context-multi-repo
Builds multi-repo context hubs and compiled markdown knowledge maps. Use when profiling repo portfolios or assembling LLM-ready cross-repo knowledge bases.