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 rules/savagelysubtle/big-brain-memory-bank/task-trackinggit clone --depth 1 https://github.com/savagelysubtle/BIG-BRAIN-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 | $0.02597 | $0.02597 |
| Opus 5 | $0.01299 | $0.01299 |
| Sonnet 5 | $0.00519 | $0.00519 |
| Haiku 4.5 | $0.00260 | $0.00260 |
Grade A, and why
task-tracking 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.
This is a copy
100% identical to task-tracking — 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 — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: Adaptive task status tracking protocol (Single Source of Truth) globs: "/memory-bank/tasks.md", "/memory-bank/activeContext.md", "**/memory-bank/progress.md" alwaysApply: false
ADAPTIVE TASK TRACKING PROTOCOL
TL;DR: Use tasks.md as the SINGLE SOURCE OF TRUTH for all task tracking. The task tracking process scales based on task complexity from Level 1 (quick bug fixes) to Level 4 (complex systems).
🚨 SINGLE SOURCE OF TRUTH RULE
Tasks.md is the ONLY file that should contain task status tracking:
- Use [ ] for pending tasks
- Use [X] for completed tasks
📝 TASKS.MD STRUCTURE
# Project Tasks
## Current Tasks
- [ ] Task 1: Description and details
- [ ] Subtask 1.1
- [ ] Subtask 1.2
- [ ] Task 2: Description and details
## Completed Tasks
- [X] Task 3: Completed on YYYY-MM-DD
- [X] Task 4: Completed on YYYY-MM-DD
🔄 ADAPTIVE TASK TRACKING BY LEVEL
Level 1: Quick Bug Fix
Update Frequency: 2-3 updates total
- Initial bug documentation
- Fix implementation
- Verification of fix
Tracking Detail:
- Single task with 1-3 checkboxes
- Focus on problem statement and solution
- Minimal but sufficient documentation
Example Task Entry:
## Current Tasks
- [ ] Fix login button not working
- [ ] Identify root cause
- [ ] Implement fix
- [ ] Verify solution
Example Update Format:
🔄 TASK UPDATE: Fix login button - [X] Complete
- Updated in tasks.md ✓
- Root cause identified: CSS z-index conflict
- Solution implemented and verified
Level 2: Simple Enhancement
Update Frequency: 4-6 updates total
- Initial task creation
- Plan finalization
- Implementation milestones (1-2)
- Testing completion
- Final verification
Tracking Detail:
- Main task with 3-5 subtasks
- Implementation approach documented
- Basic testing steps included
Example Task Entry:
## Current Tasks
- [ ] Add logout button to navbar
- [ ] Create button component
- [ ] Add logout functionality
- [ ] Style button to match design
- [ ] Add tooltip/confirmation
- [ ] Test functionality
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 · 394 lines · 2,597 tokens per session scan A e47ef7487b17
task-tracking is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It adds 2,597 tokens to every session, about $0.0130 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to task-tracking, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
skill-workflows
Capabilities catalog for cursor-kenji skills. Routes requests to the right skill or bundled workflow. Always-on routing index — the agent consults this to pick between individual skills and bundled workflows.
composer-2.5-execution
Guard execution of approved plan/burndown work: forbid reward hacking and feature deletion; require checkpoints, context discipline, safe terminal use, and fresh verification. Apply to approved plan-.md, complete-everything, or burndown-full runs; binding for any implementation model.
verification-before-completion
Require fresh, scope-appropriate evidence before any completion claim. Distinguishes implemented, locally verified, repository-green, PR-green, deployed, and observed-stable states.
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.
clarify-first
Infer-and-act by default — ask only on high confusion weight, after inspecting, with a decision-linked question.