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.
git clone --depth 1 https://github.com/savagelysubtle/BIG-BRAIN-Memory-BankWrote 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/rules/savagelysubtle/big-brain-memory-bank/context-minimal-mode)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/context-minimal-mode"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/context-minimal-mode.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 | $0.00992 | $0.00992 |
| Opus 5 | $0.00496 | $0.00496 |
| Sonnet 5 | $0.00198 | $0.00198 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
context-minimal-mode 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 6d 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.
This is a copy
100% identical to context-minimal-mode — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MINIMAL MODE: CONTEXT OPTIMIZATION
TL;DR: Use this minimal mode reference when context window space is limited. It contains only essential instructions for each workflow phase.
🚨 CORE WORKFLOW - ONE-LINE ESSENTIALS
- INIT: Check Memory Bank files → State task objective → Create section tracking list
- DOCS: Update Memory Bank files → Include platform-specific information
- PLAN: Create steps with [ ] markers in tasks.md → Include specific deliverables
- IMPL: Use tools when possible → Execute ONE command at a time → Update task status in tasks.md
- REFLECT: Document 4 required sections → Include specific items
- ARCHIVE: Archive with required format → Create cross-links
📋 TEMPLATE: SECTION TRACKING
## Section Progress
[ ] 1. INITIALIZATION
[ ] 2. DOCUMENTATION SETUP
[ ] 3. TASK PLANNING
[ ] 4. IMPLEMENTATION
[ ] 5. REFLECTION
[ ] 6. ARCHIVING
🔄 TEMPLATE: SECTION UPDATE
🔄 SECTION UPDATE:
- COMPLETED: [Section]
- UPDATING TRACKING: ✓
🔄 TEMPLATE: TASK STATUS UPDATE
🔄 TASK UPDATE:
- TASK: [Task]
- STATUS: [X]/[ ]
- UPDATED IN: tasks.md ✓
📝 TOOL USAGE PRIORITIES
Use these preferred tools when available:
list_dir- For listing directory contents (not dir/ls)edit_file- For creating/editing files (not echo/touch)read_file- For examining file contents- Use relative paths directly with tools (no cd needed)
run_terminal_cmd- For terminal commands (ONE AT A TIME)
📝 TEMPLATE: COMMAND EXECUTION
### Command: [Brief Description]
Purpose: [Explanation]
```bash
[command]
Result: [Outcome]
## ⚠️ COMMAND SAFETY (PREVENT CRASHES)
- NEVER chain commands with && or similar
- NEVER use mkdir -p for nested directories
- NPM commands CAN include multiple packages: `npm install react react-dom`
- But NEVER chain npm commands: `cd dir && npm install` WILL CRASH
## 📝 TEMPLATE: REFLECTION FORMAT
REFLECTION
What Went Well
- [Item 1]
- [Item 2]
- [Item 3]
Challenges
- [Item 1]
- [Item 2]
Lessons Learned
- [Item 1]
- [Item 2]
- [Item 3]
Improvements for Next Time
- [Item 1]
- [Item 2]
- [Item 3]
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.
- 6d ago First seen · 162 lines · 992 tokens per session scan A 805b46c24696
context-minimal-mode is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It adds 992 tokens to every session, about $0.0050 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to context-minimal-mode, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
wrapup
End-of-session wrap-up: summarizes the session and pushes a log to the project's linked NotebookLM notebook. Activate with @wrapup in chat, or "wrap up", "save this session", or "end of session".
memory-bank
You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…
search-routing
Smart Search Routing — always use QMD semantic search when available, never bypass with grep for vault content.
composer-coding-excellence
Coding craft — surgical edits, convention matching, no scope creep, no slop comments, no fabricated APIs.
clarify-first
Infer-and-act by default — ask only on high confusion weight, after inspecting, with a decision-linked question.
composer-debugging
Root-cause debugging — reproduce, trace data flow, test cheapest hypothesis, fix the cause not the symptom.