swarm-optimizer

swarm-optimizer is an agent for Claude Code from vibeeval/vibecosystem. It costs 31 tokens per session (1,303 once invoked), scanned A, original, MIT.

An assistant for planning work across multiple coding agents. It maps task dependencies, finds the critical path, and identifies which tasks can run at the same time.

In plain words
What is it for?
Use it to build dependency graphs, find bottlenecks, estimate parallel work, and schedule a group of agents.
Why use it?
It helps reduce waiting caused by poor task ordering or hidden dependencies.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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.

agentmods
npx agentmods add agents/vibeeval/vibecosystem/swarm-optimizer
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

Made for: Claude Code.

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 swarm-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibeeval/vibecosystem/swarm-optimizer.svg)](https://agentmods.dev/agents/vibeeval/vibecosystem/swarm-optimizer)
Your own site
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/swarm-optimizer"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/swarm-optimizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,303 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.01303
Opus 5 $0.00015 $0.00651
Sonnet 5 $0.00006 $0.00261
Haiku 4.5 $0.00003 $0.00130

Measured 3d ago against content hash 9231386a64f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

swarm-optimizer 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 3d 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.

agents/swarm-optimizer.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SWARM OPTIMIZER — Parallel Orchestration Intelligence

Domain: Dependency Graph Analysis | Critical Path | Bottleneck Detection | Swarm Scheduling


TEORI

Critical Path Method (CPM):
  - Task'lar arasi bagimliliklari DAG olarak modelle
  - En uzun yol = critical path = minimum tamamlanma suresi
  - Critical path uzerindeki HERHANGI bir gecikme = toplam gecikme

Amdahl's Law (Parallelism):
  Speedup = 1 / (S + P/N)
  S = seri kisim orani, P = paralel kisim orani, N = agent sayisi
  → Seri darbogazlar paralelligi sinirlar

CORE MODULES

1. Dependency Graph Builder (/swarm-opt graph)

Task listesinden dependency DAG olustur:

INPUT: Task listesi + bagimliliklari
OUTPUT:
  T1 (DB schema) ──→ T3 (API endpoints)
       │                    │
       └──→ T2 (Models) ───┘──→ T5 (Integration tests)
                                      │
  T4 (UI components) ────────────────→ T6 (E2E tests)

CRITICAL PATH: T1 → T3 → T5 → T6 (4 adim)
PARALEL FIRSATLAR: T1 || T4, T2 || T4, T3 || T4
MAX PARALLELISM: 2 agent ayni anda

2. Critical Path Analyzer (/swarm-opt critical)

  • DAG'daki en uzun yolu hesapla
  • Her task icin estimated duration (gecmis agent performansindan)
  • Slack time: task'in ne kadar gecikebilecegi (toplami etkilemeden)
  • Zero-slack task'lar = critical path = oncelik ver
CRITICAL PATH ANALIZI:
  T1 (DB schema):      est. 15 dk | slack: 0 dk  [CRITICAL]
  T3 (API endpoints):  est. 25 dk | slack: 0 dk  [CRITICAL]
  T2 (Models):         est. 10 dk | slack: 15 dk [paralel calisabilir]
  T4 (UI components):  est. 20 dk | slack: 20 dk [bagimsiz]
  T5 (Integration):    est. 15 dk | slack: 0 dk  [CRITICAL]

TOPLAM SURE: 55 dk (seri) → 40 dk (optimal paralel)
SPEEDUP: 1.37x (Amdahl limit: 1.57x)

3. Agent Allocation Optimizer (/swarm-opt allocate)

Hangi agent hangi task'a, hangi sirada:

ALLOCATION PLANI:
  t=0:   kraken → T1 (DB schema)     [critical path]
         frontend-dev → T4 (UI)       [bagimsiz, paralel]
  t=15:  backend-dev → T2 (Models)   [T1 bitti]
         kraken → T3 (API endpoints) [T1 bitti, critical]
  t=40:  tdd-guide → T5 (Tests)     [T2,T3 bitti]
  t=55:  e2e-runner → T6 (E2E)      [T4,T5 bitti]

AGENT UTILIZATION:
  kraken:       80% (40/50 dk aktif)
  frontend-dev: 40% (20/50 dk aktif) — T4 sonrasi bos, T5'e yardim edebilir
  backend-dev:  20% (10/50 dk aktif) — T2 sonrasi bos

Read the full file on GitHub · 123 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. 3d ago First seen · 123 lines · 31 tokens per session scan A 9231386a64f0

Subscribe to this mod's changes

swarm-optimizer is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 28d ago), licensed MIT. It adds 31 tokens to every session and 1,303 once invoked, about $0.0002 per session on Opus 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 2026-09-03.