A command-line workflow for sending tasks to one or more coding agents, saving their raw answers, and combining their results.

Use it to run explicit provider and model combinations, stream responses, perform read-only reviews, and organize chained or synthesized agent outputs.

It makes multi-agent reviews and debates repeatable while keeping the intermediate answers available as files.

mco-cli — Skill by mco-org

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/mco-org/mco/mco-cli

Any agent

npx skills add mco-org/mco --skill mco-cli

Clone the repo

git clone --depth 1 https://github.com/mco-org/mco

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,297 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.

Model	Per session	Once invoked
Fable 5	$0.00038	$0.01297
Opus 5	$0.00019	$0.00648
Sonnet 5	$0.00008	$0.00259
Haiku 4.5	$0.00004	$0.00130

Measured 3d ago against content hash 02abdd93bbf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mco-cli 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/mco-cli/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCO CLI Skill

Use this Skill when an upstream Agent needs to dispatch one task to one or more coding Agents and preserve their raw operational answers.

Before execution

Confirm the provider/model team with the user in natural language. Do not infer consent from installed binaries. Use either:

--agent [alias=]provider:model once per invocation; or
--providers provider,... for one default-model invocation per provider.

--agent is the model-qualified form. It supports repeated models from one provider when each repeated invocation has a distinct alias:

mco run --repo . --prompt "Inspect the parser." \
  --agent fast=pi:fast-model \
  --agent careful=pi:careful-model \
  --result-mode stdout

--providers pi,codex is an invocation-native shorthand. MCO resolves each provider's configured/default model and runs the resulting invocations through the same runtime; it is not a legacy execution path.

If MCO returns provider_selection_required, ask the user which Agents to use and retry with an explicit --providers or --agent selection.

Execution defaults

mco run defaults to --execution-mode write.
mco review is a thin read-only preset and defaults to --execution-mode read_only.
Review passes the explicit prompt unchanged. With no prompt, it uses a short natural-language review prompt; it does not inject a findings schema.
Use --execution-mode yolo only after the user explicitly requests unrestricted execution.

Output and status

MCO returns raw Agent answer text plus operational metadata. It does not infer findings, severity, confidence, consensus, or decisions from answer prose.

Default text mode streams answer deltas to stdout. With multiple invocations it adds source labels between answers but does not rewrite answer content.
--json prints one final JSON envelope.
--stream jsonl prints JSONL events; each invocation's output_delta values concatenate to its formal answer.
Progress, warnings, and provider diagnostics go to stderr. stdout remains answer text or the selected machine protocol.
status is complete, partial, or failed; exit codes are 0, 1, and 2 respectively. A cancelled or timed-out invocation is recorded inside the corresponding task status.

Read the full file on GitHub · 90 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

3d ago First seen · 90 lines · 38 tokens per session scan A 02abdd93bbf3

Subscribe to this mod's changes

mco-cli is a skill published in the GitHub repository mco-org/mco (507 stars, last pushed 20d ago), licensed MIT. It adds 38 tokens to every session and 1,297 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.

Building agents ai-agents claude cli codex developer-tools

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens