giladbarnea/soft-skills / plugins/soft-skills/skills/ai-to-delegated
ai-to-delegated
VerifiedBest practices for getting a step-function leap in productivity when working with other AI’s. Load `ai-to-delegated` before spawning a sub-agent, creating a team, talking to a teammate agent, or writing a doc likely read by other agents. Trigger words include “dispatch an agent”, “spawn a team”, and “fork the session to ...”.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.9 KB |
| briefing/examples.md | markdown | 12.7 KB |
| briefing/forked-context.md | markdown | 613 B |
| briefing/fresh-context.md | markdown | 1.6 KB |
| configurations/colloquium.md | markdown | 2.2 KB |
| configurations/external-advisor.md | markdown | 1.1 KB |
| configurations/hillclimber-watcher/protocol.md | markdown | 4.0 KB |
| configurations/hillclimber-watcher/watcher.md | markdown | 1.5 KB |
| configurations/pair-programming.md | markdown | 5.1 KB |
| configurations/research-fanout.md | markdown | 2.8 KB |
| coordination/budget-balancing.md | markdown | 1.0 KB |
| coordination/delegates.md | markdown | 4.9 KB |
| coordination/leading-leaders.md | markdown | 4.2 KB |
| coordination/many-hours-supervision.md | markdown | 3.6 KB |
| coordination/peers.md | markdown | 2.4 KB |
| planning/choose-configuration.md | markdown | 7.9 KB |
| planning/dispatch-outside-the-harness.md | markdown | 1.3 KB |
| planning/when-to-delegate.md | markdown | 8.7 KB |
coordination/delegates.md
View on GitHub---
name: delegates
description: Supervise delegates without taking over their scope, and handle approvals, escalations, and context limits.
---
# Coordinate Delegates
Read this before dispatching and while supervising delegates.
For your own reports and requests for approval, read [ai-to-leader](ai-to-leader/SKILL.md).
If your delegates lead their own agents, also read [leading-leaders.md](coordination/leading-leaders.md).
If you need to brief a delegate without shared context, read [fresh-context.md](briefing/fresh-context.md).
## Leader conduct: a delegate’s scope is not yours
Your fingers are delegation buttons. Do not row, raise sails, or scout ahead yourself unless your own leader instructs you to do so. Delegate the operational work to your delegates.
Avoid the helicopter parenting failure mode: Whatever you delegated is not yours until it returns. While a delegate works, do not do its work, do not re-read the files it is writing “just to make sure everything is okay,” and do not run its code and tests yourself to “make sure they really work.” Do not continuously poll its status either. Trust your delegate, exactly as your leader trusts you. Answer escalations, steer on exception, then step back out. This applies per delegated scope, however small the delegation.
## Brief the bottom line, not the how
This applies to every brief, whether the delegate inherits your context or starts cold. Your delegate is as intelligent as you are and navigates uncertainty well without spoon-feeding. Think: what kind of input do YOU thrive on? You, and your delegate, thrive on wide contextual understanding (is) and an explicitly stated desired end state, the intent (should). A and Z, 0 and 1.
Just *declare the bottom line added value YOU are seeking for yourself*, and why the delegate was dispatched. Do not specify which steps to take. Avoid prescribing instructions, giving “how-to” examples, listing what to think about, or dictating which files, symbols, or paths to look at. Avoid any form of hinting at possible answers to your own query. This is a serious footgun and a form of leakage that makes the delegate a waste of time, money and intelligence. All these “Don’ts” are forms of overfitting. Leaving them out frees the agent to find the best way to reach *your* goal, unbiased and unconstrained by your own assumptions.
By default, do not add guardrails to a brief or instruction. Guardrails, or unprovokedly breaking a task down into a specific, rigid, finite set of subtasks, are allowed only in two narrow cases:
1. The human wrote guardrails or was specific in their request. Just relay what they said. This is not adding limitations; it is merely adhering to the principle of passing the input faithfully, nigh-verbatim.
2. You are sharing a scar that actually happened for that specific request, so you have proof that with the same input, the subagent is prone to repeat that mistake.
If no one has made that mistake when given the input, the delegate will not make it either when given the input.
Read [examples.md](briefing/examples.md) if you have not already for contrasting examples.
## The escalation bar
The chain processes at every rung: each agent surfaces to its leader only what needs the leader’s judgment. Reversible implementation tuning is yours to decide. What legitimately goes up: product-visible behavior, money, direction and scope changes, non-trivial cross-scope decisions, and blockers.
**Batch approvals.** When you expect several approvals to arrive close together, hold them and bring one grouped request. One decision session beats three interruptions. A lone question does not wait for company.
**Suggest, then get approval**, unless your leader has already approved this kind of delegation.
## Understand an Escalation Before Passing It Up
**If you cannot explain the escalation, the question goes back down, not up.** You are a translator between decks, not a relay. When a delegate’s escalation is saturated with internal jargon you cannot ground in product terms, ask the delegate for the missing context first. Forwarding it upward verbatim is a chain-of-command failure even though the message flowed through the right rungs.
### Heavy delegation
When doing heavy delegation (multiple serial runs of heavy concurrent shapes for a complex, large task scope), avoid micromanaging pitfalls such as re-reading files your sub-agents wrote or edited "just to make sure everything is okay," running the code and tests yourself to "make sure they really work," and reading files before prompting a sub-agent when your sub-agents should read them to finish their tasks, "just to have the right context yourself.". Verify with the user whether they consider what you’re doing as "heavy delegation."
### Keep your ship afloat
For your own context window and your delegates' windows, follow [context window](soft-skills/context-window.md).
When a delegate needs to write a handoff, direct it to the [handoff skill](handoff/SKILL.md).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |