team-lead-efficiency

A set of rules for an agent coordinating several sub-agents, meaning smaller agents working on separate parts of a task.

In plain words
What is it for?
Use it to divide work into manageable tasks, assign files to one owner, launch independent tasks together, and handle shared changes centrally.
Why use it?
It reduces duplicated work, unclear ownership, excessive polling, and coordination overhead.

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/gosha70/code-copilot-team/team-lead-efficiency
Clone the repo
git clone --depth 1 https://github.com/gosha70/code-copilot-team

Made for: Cursor.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,835 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 $0.00023 $0.01835
Opus 5 $0.00012 $0.00918
Sonnet 5 $0.00005 $0.00367
Haiku 4.5 $0.00002 $0.00184

Measured 2d ago against content hash 9e5fc31116e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

team-lead-efficiency 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 2d 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.

adapters/cursor/.cursor/rules/team-lead-efficiency.mdc · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Team Lead Efficiency

Rules for the lead agent when coordinating sub-agents to minimize waste and maximize throughput.

Task Scoping

Right-Size the Work

  • 2-3 teammates is the sweet spot for most features. More than 3 increases coordination overhead without proportional speedup.
  • Each teammate task should take 5-30 minutes. If a task takes over an hour, it's too large — break it up.
  • If a task would touch fewer than 3 files, the lead should do it directly instead of delegating.

Non-Overlapping Ownership

Every file must have exactly ONE owner for a given phase:

Bad:

Agent A: Implement product service (touches product model, router, UI)
Agent B: Implement order service (also touches product model for inventory)

Good:

Agent A: Implement product service (owns product.service, product.router)
Agent B: Implement order service (owns order.service, order.router)
Lead: Handles shared code (product model changes for inventory) after both complete

The lead handles shared/cross-cutting code after teammates return — not in parallel.

Clear Boundaries in the Delegation Prompt

Every delegation must include:

  1. Exact files to create or modify (not "implement the feature").
  2. Read-only context files — schema, types, design docs the agent should reference but NOT modify.
  3. Interface contracts — what inputs/outputs must match.
  4. What NOT to do — explicit exclusions prevent scope creep.

Polling Discipline

Do Not Busy-Wait on Teammates

After launching sub-agents, the lead should:

  1. Launch all independent agents at once (parallel, not sequential).
  2. Work on non-overlapping tasks while waiting (documentation, tests, review plans).
  3. Check status periodically — not continuously. Polling once per minute is sufficient.
  4. Never re-do teammate work. If a teammate is slow, wait or stop them — don't duplicate their output.

When to Stop a Teammate

Stop a running teammate if:

  • Its task is no longer needed (requirements changed).
  • The lead has already completed the work (this means the task was mis-delegated).
  • The agent has been running over 2x the expected duration with no progress.

Read the full file on GitHub · 144 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. 2d ago First seen · 144 lines · 23 tokens per session scan A 9e5fc31116e8

Subscribe to this mod's changes

team-lead-efficiency is a cursor rule published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 1,835 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.