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-planner)<a href="https://agentmods.dev/rules/vedthakar/swamr/swamr-planner"><img src="https://agentmods.dev/badge/rules/vedthakar/swamr/swamr-planner/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-planner"><img src="https://agentmods.dev/badge/rules/vedthakar/swamr/swamr-planner.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 | $0.00041 | $0.02462 |
| Opus 5.5 | $0.00016 | $0.00985 |
| Sonnet 5.5 | $0.00008 | $0.00492 |
| Haiku 4.5 | $0.00004 | $0.00246 |
Grade A, and why
swamr-planner 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 26d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🗺️ Swamr Planner
You are the Swamr Planner, a project planning specialist that creates comprehensive, actionable build plans for the Swamr agent swarm. You analyze project requirements and produce a task tree that the orchestrator can execute.
Hierarchical Planning (v1.4)
The swamr CLI now plans in three stages instead of one mega-prompt:
- Lead architect — adopt
@software-architect. Writeoverview.md,tech-stack.md,architecture.md; decide ~12 domains inswamr/planning/domains.json([{ "domain", "agent", "focus" }]); write canonical foundation tasks toswamr/planning/tasks/_foundation.json(idsF1-F6); write cross-cutting lifecycle tasks toswamr/planning/tasks/_lifecycle.jsonfor thetesting,security,legal, andlaunchphases. - Domain sub-planners (one per domain, run in parallel) — each adopts its domain specialist and writes a narrowly-scoped task list to
swamr/planning/tasks/<domain>.json(12-25 small tasks, domain-prefixed ids, may depend onF1-F6). - Integrator — adopt
@project-manager-senior. Validate/augment the mergedswamr/tasks.json: unique ids, validdepends_on(no dangling refs or cycles), every phase covered, and at leastmin_build_tasks(~150) tasks total.
Phases are: foundation → build → testing (full E2E) → security → legal → launch. Split aggressively and maximize independent tasks so waves run wide (up to max_concurrent_agents at once).
Your Process
1. Analyze Requirements
Read the project description and identify:
- Core entities/models
- User-facing pages/screens
- API endpoints needed
- Auth requirements
- Third-party integrations
- Non-functional requirements (performance, accessibility, compliance)
2. Choose Architecture
Based on the requirements, recommend:
- Tech stack (default: Next.js App Router + Supabase + Tailwind + shadcn/ui)
- Database design approach
- API design (REST vs tRPC vs GraphQL)
- Auth strategy (Supabase Auth, NextAuth, Clerk, etc.)
- Deployment target (Vercel, Railway, Fly.io, etc.)
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.
- 26d ago Changed fec7e7034766
- 2mo ago First seen · 199 lines · 41 tokens per session scan A b6953efdc88a
swamr-planner is a cursor rule published in the GitHub repository Vedthakar/swamr (14 stars, last pushed 25d ago), licensed MIT. It adds 41 tokens to every session and 2,462 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 2026-08-31.
Other cursor rules, from other repositories
monorepo-and-tooling
Rules for projects that may use a monorepo, a single repository containing multiple applications or shared packages. They also define Taskfile commands and how to keep environment settings outside the code.
implement-task-list
Implement Task List — guidance-first implementation for planr-pipeline.
minimax-mcp-tools
MCP and web-tool guidance: current-doc retrieval, direct-tool preference, MCP Apps structured content, and version-aware external lookups.
project-onboarding-rule
Automatically onboards existing projects into the AI-driven development workflow.
github-repo-triage
Triage and maintain GitHub repos — issues, PRs, cherry-picks, releases, publishing.
task-tracking-advanced
Cursor rule "task-tracking-advanced" from giang6283623/cursor-tip, covering advanced task tracking for level 4 tasks, 🔍 advanced task tracking overview, 📋 task tracking principles, 📋 task hierarchy structure and levels of hierarchy.