---
id: "nr-fatih-arslan-runs-his-agent-fleet-from-markdown-plans-5b07d4"
slug: "fatih-arslan-runs-his-agent-fleet-from-markdown-plans-5b07d4"
title: "Fatih Arslan runs his agent fleet from Markdown plans in Git"
observed_at: "2026-09-18T13:21:28.557+00:00"
record_date: "2026-09-18"
date_kind: "observed_at"
novelty: "new"
source_platform: "arslan.io"
topics: ["coding-agents","agent-orchestration"]
entities: ["Cursor","Cursor Projects"]
related_patterns: []
source_url: "https://arslan.io/2026/09/11/how-i-manage-my-agents"
source_urls: ["https://arslan.io/2026/09/11/how-i-manage-my-agents"]
basket: {"id":"0325e6b8-f527-4f9b-bfa3-3f30e57f380b","revision":1,"cluster_id":"5b07d454-8fcf-464a-b083-cac36fc64104"}
type: "post"
description: "Fatih Arslan describes managing a fleet of coding agents through Markdown plan files in a Git repository, later driven by Cursor Projects coordinators."
why_it_matters: "The account describes one practitioner's workflow and does not establish how it compares with other orchestration setups or larger fleets. Other Projects users publishing similar plan layouts with merge rates or failure counts would show whether the pattern generalises."
verification_level: "source-inspected"
signal_type: "field_note"
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:fatih-arslan-runs-his-agent-fleet-from-markdown-plans-5b07d4"
retrieval_nugget: "Fatih Arslan describes managing a fleet of coding agents through Markdown plan files in a Git repository, later driven by Cursor Projects coordinators. Fatih Arslan, writing on his personal blog on September 11, 2026, describes managing a fleet of agents through plain Markdown plans stored in a dedicated Git repository. A /plan-init skill creates drafts, next, open, done and discarded"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:1f049b02891bf1d3e068a6769d2a85736637e0b018ac9dd2945392387a5385cd","reviewed_at":"2026-09-24T13:28:46Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":1,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"The central idea is that a versioned folder of human-readable plans can serve as the control surface for many agents.","observed_facts":[{"text":"Each plan is a single Markdown file stored in a dedicated repository accessible to cloud agents and co-workers.","source_urls":["https://arslan.io/2026/09/11/how-i-manage-my-agents"]},{"text":"The /plan-sync skill checks recorded pull requests against the dispatched plan and moves matching plans to done.","source_urls":["https://arslan.io/2026/09/11/how-i-manage-my-agents"]},{"text":"Coordinators in Cursor Projects can subscribe to pull requests, watch Slack channels or wake up on a schedule.","source_urls":["https://arslan.io/2026/09/11/how-i-manage-my-agents"]}],"mechanism":"The mechanism is a division of labour: /plan-write uses a higher reasoning model to prove a cause and name the change, so /plan-dispatch can hand a complete plan to a fast coding agent that opens a pull request.","why_now":"The timing matters because Arslan now runs these plans through coordinators, the long-running agents Cursor introduced with Projects, which subscribe to pull requests, Slack channels or schedules.","implications":["Teams adopting coordinators should keep durable plan state outside any single agent session."],"evidence_boundary":"The account describes one practitioner's workflow and does not establish how it compares with other orchestration setups or larger fleets.","watch_conditions":["Other Projects users publishing similar plan layouts with merge rates or failure counts would show whether the pattern generalises."],"related_records":[],"new_branch_reason":"It documents a concrete, file-based pattern for agent orchestration that is distinct from dashboard or memory-based approaches."}
routes: {"html":"https://newruntime.com/posts/fatih-arslan-runs-his-agent-fleet-from-markdown-plans-5b07d4/","markdown":"https://newruntime.com/posts/fatih-arslan-runs-his-agent-fleet-from-markdown-plans-5b07d4.md","json":"https://newruntime.com/posts/fatih-arslan-runs-his-agent-fleet-from-markdown-plans-5b07d4.json"}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
---

# Fatih Arslan runs his agent fleet from Markdown plans in Git

## Retrieval answer

Fatih Arslan describes managing a fleet of coding agents through Markdown plan files in a Git repository, later driven by Cursor Projects coordinators. Fatih Arslan, writing on his personal blog on September 11, 2026, describes managing a fleet of agents through plain Markdown plans stored in a dedicated Git repository. A /plan-init skill creates drafts, next, open, done and discarded

Fatih Arslan, writing on his personal blog on September 11, 2026, describes managing a fleet of agents through plain Markdown plans stored in a dedicated Git repository. A /plan-init skill creates drafts, next, open, done and discarded folders plus a README index, and skills named /plan-add, /plan-write, /plan-dispatch, /plan-sync and /plan-status move each plan through those states.

The central idea is that a versioned folder of human-readable plans can serve as the control surface for many agents. The mechanism is a division of labour: /plan-write uses a higher reasoning model to prove a cause and name the change, so /plan-dispatch can hand a complete plan to a fast coding agent that opens a pull request. Because the plans sit in Git, agents already know how to work with them, and history comes for free.

The timing matters because Arslan now runs these plans through coordinators, the long-running agents Cursor introduced with Projects, which subscribe to pull requests, Slack channels or schedules. He commits coordinator notes to the same repository, which mattered when a platform bug left a session stuck in an error loop after roughly 460 messages. Teams adopting coordinators should keep durable plan state outside any single agent session.

The account describes one practitioner's workflow and does not establish how it compares with other orchestration setups or larger fleets. Other Projects users publishing similar plan layouts with merge rates or failure counts would show whether the pattern generalises.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Coding Agents](https://newruntime.com/topics/coding-agents.md): Explore the coding-agents topic hub.
- topic hub: [Agent Orchestration](https://newruntime.com/topics/agent-orchestration.md): Explore the agent-orchestration topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)