orchestrate

orchestrate is a cursor rule for Cursor from rajitsaha/100xprism. It costs 27 tokens per session (696 once invoked), scanned A, original, MIT.

A workflow guide for handling complex tasks with several dependent steps or important design decisions. It emphasizes writing a plan first, dividing independent work, and tracking progress.

In plain words
What is it for?
Use it to plan multi-step projects, split research or implementation into separate workstreams, coordinate subagents, and recover when the work changes direction.
Why use it?
It helps prevent missed steps, confused responsibilities, and unplanned coding during large or complicated tasks.

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/rajitsaha/100xprism/orchestrate
Clone the repo
git clone --depth 1 https://github.com/rajitsaha/100xprism

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 orchestrate

README.md
[![agentmods](https://agentmods.dev/badge/rules/rajitsaha/100xprism/orchestrate.svg)](https://agentmods.dev/rules/rajitsaha/100xprism/orchestrate)
Your own site
<a href="https://agentmods.dev/rules/rajitsaha/100xprism/orchestrate"><img src="https://agentmods.dev/badge/rules/rajitsaha/100xprism/orchestrate.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 696 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 $0.00027 $0.00696
Opus 5 $0.00014 $0.00348
Sonnet 5 $0.00005 $0.00139
Haiku 4.5 $0.00003 $0.00070

Measured yesterday against content hash 18e002f8406d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrate 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 yesterday.

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/orchestrate.mdc · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrate — Complex Task Orchestration

Apply workflow orchestration methodology for multi-step tasks with 3+ steps or architectural decisions.

How to use

  • /orchestrate <task> — plan-first approach for any non-trivial task

Methodology

1. Plan first (invoke writing-plans skill)

Always start by invoking the writing-plans skill (or native plan mode if your platform has it) to produce a structured plan with TDD-style task steps. Write it to wherever writing-plans puts plans for this repo — do not assume a fixed path. Do not proceed to coding until the plan is written and reviewed.

  • If something goes sideways mid-task: STOP, re-plan using writing-plans again
  • Track progress via tasks/todo.md checkboxes

2. Use subagents (fan out independent work)

  • Offload research, exploration, and parallel analysis to subagents
  • Keep main context window clean and focused
  • One task per subagent for precision
  • Invoke the subagents skill for the fan-out ladder and standard return contract

Once the plan splits into independent workstreams, do not implement them serially. Fan them out using the ladder from the subagents skill (Workflow tool → parallel subagents → serial fallback):

plan (writing-plans)
  → parallel implementation subagents     # one per independent workstream, isolated
      each returns { summary, files[], diff, risks[], confidence }
  → gather the structured diffs
  → independent reviewer subagent          # fresh context, runs /code-review — no self-review bias
      returns { findings[]{severity,file,detail}, verdict }
  → merge / verify gate                    # apply, run /gate, only then mark done

Reference dispatching-parallel-agents and subagent-driven-development for the mechanics. Use worktree isolation when subagents edit files in parallel so they don't collide. Workstreams that share state (same module, ordering dependency) stay serial.

Read the full file on GitHub · 76 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. yesterday First seen · 76 lines · 27 tokens per session scan A 18e002f8406d

Subscribe to this mod's changes

orchestrate is a cursor rule published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 696 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 2026-09-03.