task-intake-router

A routing guide for choosing how a coding task should be handled in Copilot CLI, including planning, direct execution, delegation, or parallel work.

In plain words
What is it for?
It is for deciding between Plan Mode, Autopilot, task agents, parallel fleet work, background delegation, and per-agent model choices.
Why use it?
It helps select an appropriate execution path before implementation begins when several options are available. It considers the task type, agent role, model tier, and whether work should run locally or in the background.

Skill for Claude CodeCodex

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 skills/drvoss/everything-copilot-cli/task-intake-router
Any agent
npx skills add drvoss/everything-copilot-cli --skill task-intake-router
Clone the repo
git clone --depth 1 https://github.com/drvoss/everything-copilot-cli

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,302 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 $0.00039 $0.02302
Opus 5 $0.00019 $0.01151
Sonnet 5 $0.00008 $0.00460
Haiku 4.5 $0.00004 $0.00230

Measured 3d ago against content hash b03d0e95a72e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-intake-router 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 3d 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.

skills/copilot-exclusive/task-intake-router/SKILL.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Intake Router

Copilot CLI gives you multiple execution paths: interactive mode, Plan Mode, Autopilot, task agents, /fleet, background delegation, and per-agent model selection. This skill turns an incoming request into an explicit routing decision so you do not default to the wrong mode out of habit.

Why This is Copilot-Exclusive

The value is not generic triage. The value is mapping work onto Copilot CLI primitives that can be combined in one session:

  • Plan Mode for structured decomposition
  • Autopilot for execution after approval
  • task agents for typed delegation (explore, task, general-purpose, code-review)
  • /fleet for parallel fan-out
  • Background delegation for cloud execution on GitHub
  • Per-agent model overrides for cost/quality optimization

When to Use

  • A new request arrives and it is unclear whether to answer, plan, implement, review, or delegate
  • The task could be handled in several ways and you want the highest-leverage path
  • You need to decide between local execution, /fleet, or cloud background delegation
  • You want an explicit model plan before spending premium tokens on the wrong step

When NOT to Use

Instead of task-intake-router Use
A tiny request with an obvious next step Do the work directly
Deep implementation after routing is already agreed The routed skill or workflow
Technology detection for repository onboarding stack-detector

Routing Dimensions

Every request should be classified on five dimensions:

  1. Intent — explain, investigate, implement, review, or operate
  2. Scope — one file, many files, or cross-cutting
  3. Dependency shape — sequential or parallelizable
  4. Risk — low, medium, or high consequence if wrong
  5. Runtime fit — local-only, GitHub-native, or cloud-friendly

Core Routing Matrix

Situation Route Why
User is asking for understanding only Interactive answer or explore agent No file changes needed
Multi-file feature with unknown scope Plan Mode → Autopilot Clarify before editing
Many independent subtasks /fleet or multiple background agents Parallelism pays off
Build/test/lint failure task agent of type task Fast execution, low-context output
Security-sensitive review code-review agent + premium model Higher reasoning quality for high-risk analysis
Long-running implementation you do not need locally Background delegation (& or /delegate) GitHub branch diff or PR becomes the output
Runtime rollout / post-ship observation deployment-canary Shipping is not the end of the workflow

Read the full file on GitHub · 276 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. 3d ago First seen · 276 lines · 39 tokens per session scan A b03d0e95a72e

Subscribe to this mod's changes

task-intake-router is a skill published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 6d ago), licensed MIT. It adds 39 tokens to every session and 2,302 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

winui-ui-testing

Automated UI testing for Windows desktop apps — generate a batch test script with the winapp ui UI Automation harness, run all tests in one pass, read results. Covers element assertions, interactions, value checking (TextBox, ComboBox, ToggleSwitch), keyboard shortcuts and typing (send-keys), hover, drag-and-drop…

microsoft/win-dev-skills · 122 tokens

pr-review

Multi-dimensional review of a PR or feature branch in microsoft/win-dev-skills. Activate on "review my PR / changes / branch", "vet before pushing", "PR review", "is this ready to merge". Fans out parallel sub-agents over skill content, the skill-vs-tool boundary (solution hierarchy), tool correctness…

microsoft/win-dev-skills · 98 tokens

winui-packaging

MSIX packaging, code signing, and distribution for WinUI 3 apps — build for release, certificate generation (winapp cert generate), certificate trust, code signing (winapp sign), self-contained deployment, CI/CD with GitHub Actions, and Microsoft Store submission. Use when preparing for release, creating MSIX…

microsoft/win-dev-skills · 86 tokens

winui-session-report

Analyze the current or a recent agent session (GitHub Copilot CLI or Claude Code) and generate a diagnostic report. Use only when the user explicitly asks for session feedback, agent debugging, or a review of what happened during a build session. Do not inspect session data automatically.

microsoft/win-dev-skills · 61 tokens

winui-wpf-migration

Migrate WPF applications to WinUI 3 — namespace replacement (System.Windows → Microsoft.UI.Xaml), control mapping (DataGrid→ListView, WrapPanel→ItemsRepeater, TabControl→TabView), threading (Dispatcher→DispatcherQueue), imaging (System.Drawing→BitmapImage), MVVM conversion to CommunityToolkit.Mvvm, and…

microsoft/win-dev-skills · 100 tokens

copilotd-e2e-verification

Perform real end-to-end validation of copilotd issue and pull request orchestration using live GitHub artifacts.

DamianEdwards/copilotd · 31 tokens