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/Vedthakar/swamrWrote 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/vedthakar/swamr/swamr-obsidian-brain)<a href="https://agentmods.dev/rules/vedthakar/swamr/swamr-obsidian-brain"><img src="https://agentmods.dev/badge/rules/vedthakar/swamr/swamr-obsidian-brain/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/vedthakar/swamr/swamr-obsidian-brain"><img src="https://agentmods.dev/badge/rules/vedthakar/swamr/swamr-obsidian-brain.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00062 | $0.01645 |
| Opus 5.5 | $0.00025 | $0.00658 |
| Sonnet 5.5 | $0.00012 | $0.00329 |
| Haiku 4.5 | $0.00006 | $0.00164 |
Grade A, and why
swamr-obsidian-brain 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 11d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧠 Swamr Obsidian Brain
You manage the project's Obsidian vault — the persistent second brain that ensures no agent ever loses context, no matter how many phases or sessions the build spans.
Vault Location
The Obsidian vault lives at swamr/brain/ inside the project directory. It is initialized by the orchestrator at project start and opened in Obsidian alongside Cursor.
Vault Structure
swamr/brain/
├── 00-project/
│ ├── overview.md # Project description, goals, constraints
│ ├── tech-stack.md # Chosen technologies and why
│ ├── architecture.md # System architecture decisions
│ └── glossary.md # Domain terms and definitions
├── 01-planning/
│ ├── requirements.md # Full requirements breakdown
│ ├── task-tree.md # Master task list with dependencies
│ ├── risk-register.md # Known risks and mitigations
│ └── decisions/
│ └── ADR-001-auth.md # Architecture Decision Records
├── 02-foundation/
│ ├── db-schema.md # Database schema with explanations
│ ├── api-design.md # API route design and contracts
│ ├── component-tree.md # UI component hierarchy
│ └── auth-flow.md # Authentication flow documentation
├── 03-build/
│ ├── phase-log.md # Running log of what was built per phase
│ ├── task-outputs/
│ │ ├── F1-scaffold.md # What each task produced
│ │ ├── B1-dashboard.md
│ │ └── ...
│ └── issues/
│ ├── bug-001.md # Issues found during build
│ └── ...
├── 04-testing/
│ ├── test-plan.md # Testing strategy
│ ├── qa-results.md # Aggregated QA results
│ └── coverage-gaps.md # Known gaps in test coverage
├── 05-hardening/
│ ├── security-audit.md # Security findings
│ ├── performance-report.md # Performance benchmarks
│ ├── a11y-report.md # Accessibility audit
│ └── legal-checklist.md # Legal compliance status
├── 06-launch/
│ ├── deploy-runbook.md # Deployment steps
│ ├── post-launch-checklist.md # Post-launch verification
│ └── handoff.md # Final handoff documentation
├── templates/
│ ├── task-output.md # Template for task completion notes
│ ├── decision-record.md # Template for ADRs
│ └── phase-summary.md # Template for phase summaries
└── index.md # Vault homepage with links to everything
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.
- 11d ago First seen · 202 lines · 62 tokens per session scan A 402b25d890c0
swamr-obsidian-brain is a cursor rule published in the GitHub repository Vedthakar/swamr (12 stars, last pushed 10d ago), licensed MIT. It adds 62 tokens to every session and 1,645 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-04.
Other cursor rules, from other repositories
project-memory
This rule guides recording project events and decisions in projectmem.
shared-agents-knowledge
Shared agents skills and learnings — automatic sync, retrieve, capture.
haive-memories
Hivelore shared memories & block sensors (auto-generated).
haive-mcp-required
Require Hivelore MCP (getbriefing / memrelevantto) before substantive repo edits.
use-profile
Always consult the user's personal profile via the mcp-me MCP server before answering.
sift-memory
Use the local sift CLI to search Claude Code, Codex, Cursor, and OpenCode chat history when prior AI coding-assistant context, session memory, implementation history, or project decisions would help.