context-minimal-mode

A shortened set of workflow instructions for situations where the agent has limited context-window space. A context window is the amount of conversation and project information the agent can keep available at once.

In plain words
What is it for?
It is for quickly checking project memory, planning work, implementing changes, updating tasks, recording reflections, and archiving completed work.
Why use it?
It preserves the essential steps when there is not enough room for the full workflow instructions.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/kfnzero/mantis-mcp-server/context-minimal-mode
Clone the repo
git clone --depth 1 https://github.com/kfnzero/mantis-mcp-server

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 992 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00992
Opus 5 $0.00000 $0.00496
Sonnet 5 $0.00000 $0.00198
Haiku 4.5 $0.00000 $0.00099

Measured 2d ago against content hash 805b46c24696, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/Core Implementation/context-minimal-mode.mdc · 162 lines

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

  1. INIT: Check Memory Bank files → State task objective → Create section tracking list
  2. DOCS: Update Memory Bank files → Include platform-specific information
  3. PLAN: Create steps with [ ] markers in tasks.md → Include specific deliverables
  4. IMPL: Use tools when possible → Execute ONE command at a time → Update task status in tasks.md
  5. REFLECT: Document 4 required sections → Include specific items
  6. 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]

Read the full file on GitHub · 162 lines

Changes

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.

  1. 2d ago First seen · 162 lines · 992 tokens per session scan A 805b46c24696

Subscribe to this mod's changes

context-minimal-mode is a cursor rule published in the GitHub repository kfnzero/mantis-mcp-server (10 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 992 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 2026-08-31.