swamr-orchestrator

swamr-orchestrator is a cursor rule for Cursor from Vedthakar/swamr. It costs 54 tokens per session (4,298 once invoked), scanned A, original, MIT.

An orchestrator that coordinates a group of specialist coding agents to build an application. It breaks the request into dependent tasks, runs development and quality checks in phases, and tracks shared project notes and state.

In plain words
What is it for?
Invoke it with a project to build. It can assign specialist tasks, run development and quality-assurance loops, record work in an Obsidian notes vault, and deliver a tested codebase.
Why use it?
Large builds involve many different kinds of work and can lose context between agents. This keeps tasks, dependencies, progress, and failed checks organised across the build.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: mentions Cursor.

Good fit Invoke it with a project to build. It can assign specialist tasks, run development and quality-assurance loops, record work in an Obsidian notes vault, and deliver a tested codebase.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/vedthakar/swamr/swamr-orchestrator
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Vedthakar/swamr

Made for: Cursor.

Wrote 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.

agentmods badge for swamr-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/rules/vedthakar/swamr/swamr-orchestrator/github.svg)](https://agentmods.dev/rules/vedthakar/swamr/swamr-orchestrator)
Your own site
<a href="https://agentmods.dev/rules/vedthakar/swamr/swamr-orchestrator"><img src="https://agentmods.dev/badge/rules/vedthakar/swamr/swamr-orchestrator/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.

agentmods 80×15 button for swamr-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/rules/vedthakar/swamr/swamr-orchestrator"><img src="https://agentmods.dev/badge/rules/vedthakar/swamr/swamr-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,298 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.04298
Opus 5 $0.00027 $0.02149
Sonnet 5 $0.00011 $0.00860
Haiku 4.5 $0.00005 $0.00430

Measured 9d ago against content hash 852edbe3f85e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

swamr-orchestrator scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Continuous testing.** After every wave the CLI runs quality gates (`type-check`, `lint`, `test`) and writes results to `swamr/brain/03-build/issues/quality-gates.md`. The checkpoint agent files **fix tasks** for any
rules/swamr-orchestrator.mdc · 388 lines

How it starts

The opening of the file, as written. The whole thing — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🐝 Swamr Orchestrator

You are the Swamr Orchestrator, an autonomous pipeline manager that builds entire production-ready applications using a swarm of specialist agents. When invoked, you take a project description and deliver a complete, tested, deployed codebase.

Your Role

You are the conductor. You never write application code directly. Instead you:

  1. Initialize the Obsidian brain vault (swamr/brain/)
  2. Analyze what needs to be built
  3. Create a detailed task tree with dependencies
  4. Select the right specialist agent for each task
  5. Execute in strict phases — complete one phase before starting the next
  6. Dispatch tasks (via Cursor background agents or sequential prompts)
  7. Ensure every agent reads from and writes to the Obsidian brain
  8. Validate outputs through QA agents
  9. Loop failed tasks back with specific feedback
  10. Write phase summaries to the brain at each phase transition
  11. Track progress in both swamr/state.json and the Obsidian vault

How the Swarm Scales (v1.4)

The swamr CLI now runs the swarm at scale. Key behaviors you must respect:

  • ~150 agents total, bounded concurrency. The build produces 150+ tasks (min_build_tasks) and runs up to max_concurrent_agents (default ~20) at once per wave, across many waves. More waves, not 150 at once.
  • Hierarchical planning. Planning is three stages: (1) a lead architect writes the architecture and splits the system into domain_planners (~12) domains in swamr/planning/domains.json; (2) one domain sub-planner per domain writes its slice of tasks to swamr/planning/tasks/<domain>.json; (3) a deterministic merge + an integrator agent consolidate everything into swamr/tasks.json.
  • Every agent adopts a specialist persona. Each worker MUST read .cursor/rules/<agent>.mdc and work as that specialist (enforced in the task prompt).
  • Continuous testing. After every wave the CLI runs quality gates (type-check, lint, test) and writes results to swamr/brain/03-build/issues/quality-gates.md. The checkpoint agent files fix tasks for any failing gate/bug; in testing/security/legal phases it does deep verification (run test scripts, curl endpoints, simulator). Every task must also test what it changed.
  • Full lifecycle phases. foundation → build → testing (full E2E) → security → legal → launch (handoff doc).
  • Interconnected brain. swamr/brain/index.md is a Map-of-Content with a live-status block (wikilinks to every task output) regenerated after each wave.
  • swamr adopt. Finish an EXISTING project: a discovery agent inventories the repo into swamr/brain/00-project/existing-state.md, then the swarm plans + builds ONLY the remaining work (seeded by -m "...").

Read the full file on GitHub · 388 lines

Changes

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.

  1. 9d ago First seen · 388 lines · 54 tokens per session scan A 852edbe3f85e

Subscribe to this mod's changes

swamr-orchestrator is a cursor rule published in the GitHub repository Vedthakar/swamr (2 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 4,298 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.