autonomous-orchestrator

A set of rules for coordinating autonomous software development in Cursor, using subagents, sprints, Git pushes, and project handoff files.

In plain words
What is it for?
Use it for autonomous development sessions involving Rust formatting, tests, linting, feature-management checks, parallel subagents, and Git-based handoffs.
Why use it?
It provides a repeatable process for inspecting a repository, delegating independent work, running checks, and recording development patterns.

Cursor rule for Cursor

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 rules/platinoff/poolai/autonomous-orchestrator
Clone the repo
git clone --depth 1 https://github.com/platinoff/poolAI

Made for: Cursor.

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,395 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 $0.00029 $0.01395
Opus 5 $0.00015 $0.00698
Sonnet 5 $0.00006 $0.00279
Haiku 4.5 $0.00003 $0.00139

Measured 3d ago against content hash 870a687ea467, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

autonomous-orchestrator 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.

.cursor/rules/autonomous-orchestrator.mdc · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Оркестратор автономної розробки (PoolAI)

Застосовуй, коли користувач запускає авторозробку, автономний прогін, посилається на AUTO_RUN_SESSION_*.md або просить «оркестратор».

Роль головного агента

Ти оркестратор, не єдиний виконавець усього репо:

  1. S0 — зріз (сам): git fetch && git status -sb; прочитай HANDOFF_NEW_SESSION.md, FUNCTION_MANAGEMENT.md §5.1–5.2, актуальний AUTO_RUN_SESSION_*.md (найновіший за датою в імені).
  2. Менеджер функціоналу (сам або subagent explore): звірка FM-* ↔ код; не дублюй повний обхід docs/ — див. .cursor/rules/functionality-management.mdc § «Охоплення docs».
  3. Код / тести (subagent shell або сам): cargo fmt, cargo test-ci, clippy-матриці лише після змін у src//tests/ (як у CI / AUTO_RUN §3).
  4. Паралельно: незалежні області (наприклад src/ui/ + src/services/) — окремі Task subagents з чітким prompt і очікуваним артефактом (файли, тести, рядки FM).
  5. Збір патернів (обов’язково в кінці P0 або S6): доповни docs/development/AUTO_DEV_PATTERNS.md — конкретні шляхи, сигнатури, команди (не загальні поради).

Субагенти (Cursor Task)

Тип Коли делегувати
explore Широкий пошук по docs/, rg по FM/Architect, інвентар маршрутів без повного читання файлів
shell MSYS2 bash: cargo test-ci, git, бенч poolai_health_load
generalPurpose Ізольована фіча з acceptance criteria (один FM або один модуль)
ci-investigator Розбір одного failed CI check (довідково)
bugbot / security-review Лише за явним запитом review; не в drain абракадабра

Не делегуй: git push, оновлення §5.1 / §5.12 FM, NEXT_SESSION_PROMPT, фінальний Summary коміта — залишай собі.

Ітераційні PH-S сесії: канон черги — FM §5.12 + NEXT_SESSION_PROMPT (не AUTO_RUN, якщо промпт не просить авторозробку).

Read the full file on GitHub · 65 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 · 65 lines · 29 tokens per session scan A 870a687ea467

Subscribe to this mod's changes

autonomous-orchestrator is a cursor rule published in the GitHub repository platinoff/poolAI (4 stars, last pushed 9d ago), licensed MIT. It adds 29 tokens to every session and 1,395 once invoked, about $0.0001 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 2026-08-31.