Agent skill · AI & Agents

outsourcerer

Interactive copilot that offloads grunt work to a cheaper engine while Claude orchestrates. Greets each session with your live token limits and a driving mode (auto-pilot / you-drive / hybrid), auto-conserves when your Claude window runs hot, and picks models by live benchmarks. Triggers: outsource, offload, delegate, conserve tokens, use GLM/Devin/Codex, or get a second opinion.

alexgreenshgithub.com/alexgreenshGitHub ↗
claude-codecodexcopilotships scriptsNOASSERTION
Install
npx skills add alexgreensh/outsourcerer --skill outsourcerer --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 86
SKILL.md size: 17 KB
Bundled scripts: yes
Path: plugins/outsourcerer/skills/outsourcerer/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 93
Language: Shell

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Outsourcerer **Created by**: [Alex Greenshpun](https://linkedin.com/in/alexgreensh) Delegate the work Claude would hand its own subagents to a cheaper or different engine instead. Model-agnostic; default `glm-5.2` (a free Devin lane). One entrypoint: ``` ${CLAUDE_PLUGIN_ROOT}/skills/outsourcerer/scripts/outsourcerer.sh <subcommand> [args] ``` Global flags (`--provider`, `--cloud-ack`) work anywhere, before or after the subcommand. You drive this script in natural language; the user should never learn a flag. If you're explaining a command instead of running it, you're doing it wrong. ## Session start: the handshake (this is the default, not raw CLI) **Every session begins by silently running `brief`** — it returns the ready lanes, the user's live limits (e.g. `claude5h=95`), and a conservation call in one shot. Greet the user with that live picture; if their driving mode is unset, present the three modes and let them pick. The choice is remembered (`~/.outsourcerer/mode`) — never ask twice. - **A) Auto-pilot** — you pick the lane/model/effort (via `advise`, see below), offload proactively, conserve automatically. Give a one-line receipt (task · model + why · permission mode · cas

What's inside
Steps it walks through
  1. Session start: the handshake (this is the default, not raw CLI)
  2. Conserve on your own (watch the fuel gauge)
  3. Pick the model with data, not vibes
  4. The verbs (verb = permission mode)
  5. Model alias → lane (the alias picks the lane; no --provider needed)
  6. Interactive by default, live-steered (non-negotiable)
  7. Watch what you launch — and report on a clock (non-negotiable)
  8. Operating rules
  9. Subcommands
  10. External-session claims
  11. References
Ships with 24 files
  • evals/evals.json
  • references/agentic-local.md
  • references/effort-and-tiers.md
  • references/jobs-and-safety.md
  • references/lanes-and-models.md
  • references/loops.md
  • references/mechanism.md
  • references/model-advisory.md
  • references/parallel-and-fanout.md
  • references/second-opinion-and-parity.md
  • references/tab.md
  • references/vocabulary-hygiene.md
  • scripts/anthropic-openai-shim.py
  • scripts/outsourcerer-winpty-broker.sh
  • scripts/outsourcerer.cmd
  • scripts/outsourcerer.ps1
  • scripts/outsourcerer.sh
  • scripts/run-or-codex.sh
  • scripts/run-or-model.sh
  • scripts/tests/conformance.sh
  • scripts/tests/test_advise.sh
  • scripts/tests/test_agentic_local_cert.py
  • scripts/tests/test_autodetach.sh
  • scripts/tests/test_bearings.sh
first 24 of 86
About this skill
What does the outsourcerer skill do?

Interactive copilot that offloads grunt work to a cheaper engine while Claude orchestrates. Greets each session with your live token limits and a driving mode (auto-pilot / you-drive / hybrid), auto-conserves when your Claude window runs hot, and picks models by live benchmarks. Triggers: outsource, offload, delegate, conserve tokens, use GLM/Devin/Codex, or get a second opinion.

How do I install it?

Run `npx skills add alexgreensh/outsourcerer --skill outsourcerer --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From alexgreensh/outsourcerer, a repository with 93 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going