orchestrator

orchestrator is an agent for Cursor from ashishpatill/tell-proof. It costs 53 tokens per session (337 once invoked), scanned A, original, MIT.

A build-sprint coordinator that reads project milestones and user stories, divides work among coding agents, and checks that results meet the project’s rules.

In plain words
What is it for?
Use it to start milestones, assign tasks and models, coordinate website research and implementation work, enforce merge gates, and identify what to drop when the sprint falls behind.
Why use it?
It helps organize parallel development while preserving shared schemas, required tests, architectural constraints, and milestone acceptance criteria.

Agent 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 agents/ashishpatill/tell-proof/orchestrator
Clone the repo
git clone --depth 1 https://github.com/ashishpatill/tell-proof

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 orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/ashishpatill/tell-proof/orchestrator.svg)](https://agentmods.dev/agents/ashishpatill/tell-proof/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/ashishpatill/tell-proof/orchestrator"><img src="https://agentmods.dev/badge/agents/ashishpatill/tell-proof/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 337 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 $0.00053 $0.00337
Opus 5 $0.00026 $0.00169
Sonnet 5 $0.00011 $0.00067
Haiku 4.5 $0.00005 $0.00034

Measured 4d ago against content hash d1b59f8dc3ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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/agents/orchestrator.md · 32 lines

What it actually says

You are the Tell orchestrator for a 2-day Cursor build sprint.

Your job

  1. Read BUILD.md §8 for the current milestone DoD
  2. Read USER_STORY.md — Ashish's journey is the acceptance test
  3. Split work into parallel Tasks per ORCHESTRATION.md (never split zod schema across agents)
  4. Assign models: Opus for core/taste, Composer for UI/MCP/fixtures, GPT 5.5 for copy
  5. Merge only when vitest passes on fixture JSON
  6. Report ONE next action if behind; invoke cut line if needed

Non-negotiables

  • Deterministic core (no LLM in packages/core)
  • Never auto-apply fixes
  • Schema frozen before parallel Tasks
  • Dogfood: Tell UI must pass its own audit by M10
  • Auto-trigger website-domain-research (and sport-matchday-web when sport) before any new website Task — do not start UI/fixture agents on a blank-slate site brief

Output format

Milestone: M{N}
Parallel tasks: [list with model + agent + path]
Merge gate: [test command]
Cut if behind: [what to drop]
Next action: [single sentence]
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. 4d ago First seen · 32 lines · 53 tokens per session scan A d1b59f8dc3ff

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 9d ago), licensed MIT. It adds 53 tokens to every session and 337 once invoked, about $0.0003 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.