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 instructions/robertmeisner/mcp_sqlite_memory_bank/generalgit clone --depth 1 https://github.com/robertmeisner/mcp_sqlite_memory_bankWhat 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 | $0.07241 | $0.07241 |
| Opus 5 | $0.03621 | $0.03621 |
| Sonnet 5 | $0.01448 | $0.01448 |
| Haiku 4.5 | $0.00724 | $0.00724 |
Grade A, and why
mcp_sqlite_memory_bank general.instructions.md 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 2d 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 — 683 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GENERAL DEVELOPMENT INSTRUCTIONS
PRIME DIRECTIVE
User/Author: Robert Meisner [email protected]
Be chatting and teach about what you are doing while coding.
First analyze the problem and requirements. Then, write a gameplan that implements the solution.
The gameplan should be well-structured, with clear next steps and comments explaining each phase.
Always provide a clear, concise summary of the changes made at the end of each edit.
If you encounter an error or unexpected behavior, stop and analyze the issue before proceeding.
Never make changes that could break existing functionality without thorough testing and validation.
As a last step review the code for any potential improvements or optimizations and execute them if needed.
COMMUNICATION PROTOCOLS
- **Explain Before Acting**: Always explain what you're about to do and why
- **Real-Time Updates**: Provide progress updates during long operations
- **Error Communication**: When errors occur, explain the error, root cause, and solution
- **Teaching Moments**: Use coding opportunities to explain best practices
- **Decision Rationale**: Always explain the reasoning behind technical decisions
- **Alternative Approaches**: Mention alternative solutions and why the chosen approach is preferred
GIT COMMIT PROTOCOLS
- **Format**: Use conventional commit format: `type(scope): description`
- **Types**: `feat`, `fix`, `refactor`, `docs`, `test`, `chore`, `perf`, `style`
- **Content**: Clear, descriptive messages explaining the change
- **Co-authored**: **NEVER include `Co-authored-by` lines** - commits should reflect actual human authorship only
- **Examples**:
- `feat: add semantic search functionality`
- `fix: resolve type error in database module`
- `refactor: eliminate code duplication in filtering logic`
KNOWLEDGE MANAGEMENT & DOCUMENTATION
If you encounter a topic or technology you are not familiar with, do not attempt to guess or make assumptions.
Instead, ask for clarification or additional information before proceeding.
Always analyze and use available MCP servers (e.g. context7 for library/package documentation) and other tools.
Store the library docs you've downloaded in the `temp/docs` directory as {lib_name}.md files for future reference.
If you need to reference external libraries or frameworks, ensure you have the latest documentation available.
Always check if the library is already downloaded in the `temp/docs` directory before asking for it.
Always prioritize accuracy and reliability over speed.
If you are unsure about a solution, take the time to research and verify before implementing it.
When you fetch documentation for any library or package, always save it as a Markdown file in temp/docs/{lib_name}.md before using or referencing it in your workflow.
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.
- 2d ago First seen · 683 lines · 7,241 tokens per session scan A c024f345511f
mcp_sqlite_memory_bank general.instructions.md is an instructions file published in the GitHub repository robertmeisner/mcp_sqlite_memory_bank (2 stars, last pushed 1y ago), licensed MIT. It adds 7,241 tokens to every session, about $0.0362 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 2026-08-31.
Other instructions, from other repositories
daisyui code_generation_with_git.instructions.md
Instructions for saadeghi/daisyui, covering activation, initial setup, development loop, error handling and session end.
planning-with-files AGENTS.md
AGENTS.md instructions for OthmanAdi/planning-with-files, covering agents.md — planning-with-files agent reference card, commit rules, release checklist (12 steps), version bump scope and changelog format.
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.
Commit Message
Comprehensive Conventional Commits guidelines for openwebui-extensions.
ai-git-commiter CLAUDE.md
Instructions for zdt1013/ai-git-commiter, covering ai git commiter, 项目结构, 技术栈, 常用命令 and 安装依赖.
stiletto CLAUDE.md
Instructions for benjamin-bader/stiletto, covering stiletto — contributor & agent guide, commit messages: conventional commits (required), breaking changes, examples and how releases work.