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/cross-linkinggit 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/cross-linking)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/cross-linking"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/cross-linking.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 | $0.00888 | $0.00888 |
| Opus 5 | $0.00444 | $0.00444 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
cross-linking 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 5d 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 cross-linking — 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CROSS-LINKING REQUIREMENTS
TL;DR: After archiving a task, create specific cross-links in progress.md to reference the archive entry, update activeContext.md with the completion status, and mark the task as completed in tasks.md. Use the exact formats shown below.
🔗 CROSS-LINKING FORMATS
After completing and archiving a task, create these cross-links:
1️⃣ In progress.md:
## Completed Tasks
- [Task Name] - Completed on YYYY-MM-DD, see [archive entry](mdc:../docs/archive/completed_tasks.md#task-task-name-v10)
2️⃣ In activeContext.md:
## Recent Completions
- [Task Name] has been completed and archived. Next focus is on [Next Task].
3️⃣ In tasks.md:
## Completed Tasks
- [X] [Task Name] - Completed on YYYY-MM-DD
📝 FORMAT DETAILS
For progress.md:
- Section title:
## Completed Tasks - Date format:
YYYY-MM-DD - Link text:
archive entry - Link format:
mdc:../docs/archive/completed_tasks.md#task-task-name-v10 - Anchor rules:
- Convert task name to lowercase
- Replace spaces with hyphens
- Add
-v10suffix (no parentheses or periods) - NOTE: This should match format
## Task: Task Name v10in archive
For activeContext.md:
- Section title:
## Recent Completions - Format:
[Task Name] has been completed and archived. Next focus is on [Next Task]. - End with period
- Use exact task names
For tasks.md:
- Section title:
## Completed Tasks - Format:
- [X] [Task Name] - Completed on YYYY-MM-DD - Use exact task names
- Keep the [X] checkbox format
🔄 CROSS-LINKING PROCEDURE
- Archive task in completed_tasks.md
- Mark task as completed in tasks.md
- Add entry to progress.md with link to archive
- Update activeContext.md with completion status
✓ CROSS-LINKING CHECKLIST
Before completing any task, verify:
- tasks.md shows task marked as [X] complete
- progress.md contains link to archive entry with exact format
- activeContext.md contains Recent Completions section with exact format
- All links are valid and working
- Task names match exactly between all files
- Date format is YYYY-MM-DD
- Link anchor format is correct (lowercase, hyphens, v10)
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.
- 5d ago First seen · 112 lines · 888 tokens per session scan A ce23163b68fa
cross-linking is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It adds 888 tokens to every session, about $0.0044 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to cross-linking, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
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.
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.
composer-deep-research
Edge-case research for audits, vendor comparisons, and unfamiliar APIs — primaries first, iterative retrieval, explicit conflicts; not the default build path.
composer-verification
Always-on proof contract — labeled completion states, proportional evidence, no fabricated success.