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/070-section-checkpoint-system)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/070-section-checkpoint-system"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/070-section-checkpoint-system.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 | $0.00000 | $0.02090 |
| Opus 5 | $0.00000 | $0.01045 |
| Sonnet 5 | $0.00000 | $0.00418 |
| Haiku 4.5 | $0.00000 | $0.00209 |
Grade A, and why
070-section-checkpoint-system 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 7d 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: WHEN tracking a multi-step task ENSURE progress tracking and verification at section boundaries globs: ["/*.md", "/*.mdc"] alwaysApply: true
TL;DR: The Section Checkpoint System ensures reliable progress tracking and verification at task section boundaries, improving task management and recovery from interruptions.
1.0.0
- Has a clear starting state and completion criteria
- Addresses a specific aspect of the overall task
- Can be verified for correctness upon completion
- Provides meaningful progress towards the goal
- Has dependencies on previous sections but not future ones
Sections should be sized appropriately for the task's complexity level.
```
## 📊 SECTION CHECKPOINT: [Section Name]
**Status**: [COMPLETE/IN PROGRESS]
**Verification**: [VERIFIED/PENDING]
### 📌 Section Summary
[Brief description of what this section accomplished]
### 🔍 Key Implementation Details
- [Important detail 1]
- [Important detail 2]
- [Important detail 3]
### 📋 Verification Steps
- [✓] [Verification step 1]
- [✓] [Verification step 2]
- [✓] [Verification step 3]
### 🧠 Insights & Learnings
- [Insight or learning 1]
- [Insight or learning 2]
### ⏭️ Next Section: [Name of next section]
[Brief description of what comes next]
```
This structure ensures consistent tracking and verification across all tasks.
- **Level 1 (Low Complexity)**
- 2-3 sections total
- Each section represents a major step
- Simplified verification (2-3 points)
- **Level 2 (Medium Complexity)**
- 3-5 sections total
- Standard verification (3-5 points)
- Basic insights documentation
- **Level 3 (High Complexity)**
- 5-8 sections total
- Comprehensive verification (5+ points)
- Detailed insights and learnings
- **Level 4 (Critical Complexity)**
- 8+ sections with potential sub-sections
- Rigorous verification process
- In-depth insights with implications
- May include stakeholder verification points
Sections should be balanced in size and scope within a given task.
1. **Completion Check**
- All planned work for the section is complete
- No open items remain within section scope
- All deliverables created and accessible
2. **Correctness Verification**
- Implementation meets requirements
- Code/content passes quality checks
- No regressions introduced
- Edge cases handled appropriately
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.
- 7d ago First seen · 298 lines · 0 tokens per session scan A c3d9e7ef02ea
070-section-checkpoint-system is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,090 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.
Other cursor rules, from other repositories
composer-coding-excellence
Coding craft — surgical edits, convention matching, no scope creep, no slop comments, no fabricated APIs.
composer-core
Always-on builder spine — continue the app, demoable slice, Build loop, Run/Wired handoff, ask only on high confusion weight.
composer-reasoning
High-stakes judgment for architectural or multi-option work — tradeoffs, one-way doors, reason-then-re-evaluate, honest pushback.
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.
composer-fullstack-delivery
New screen, feature, endpoint, or multi-layer slice — freeze seams, ship one demoable path, failure modes, Run/Wired handoff.