ck:team

A tool for coordinating several independent coding-agent sessions on one task. The sessions can research, write code, review changes, or debug in parallel.

In plain words
What is it for?
Use it for research, implementation, code review, or debugging workflows that benefit from multiple teammates.
Why use it?
It divides large tasks among separate agents and keeps their work coordinated through shared tasks and messages.

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/manhvann/codexkit/team
Any agent
npx skills add manhvann/codexkit --skill team
Clone the repo
git clone --depth 1 https://github.com/manhvann/codexkit

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,182 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 $0.00030 $0.03182
Opus 5 $0.00015 $0.01591
Sonnet 5 $0.00006 $0.00636
Haiku 4.5 $0.00003 $0.00318

Measured 2d ago against content hash 8466b23b54d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ck:team 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.

.agents/skills/team/SKILL.md · 286 lines

How it starts

The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Teams - CK-Native Orchestration Engine

Coordinate multiple independent Codex sessions. Each teammate has own context window, loads project context (AGENTS.md, skills, agents), communicates via shared task list and messaging.

Requires: Agent Teams enabled. Set CODEX_EXPERIMENTAL_AGENT_TEAMS=1 in settings.json env if using Codex < 2.1.33. May be GA in 2.1.33+.

Usage

$team <template> <context> [flags]

Templates: ck:research, ck:cook, ck:code-review, ck:debug

Flags:

  • --devs N | --researchers N | --reviewers N | --debuggers N — team size
  • --plan-approval / --no-plan-approval — plan gate (default: on for cook)
  • --delegate — lead only coordinates, never touches code

Execution Protocol

Pre-flight (MANDATORY — merged into step 2 of every template):

  1. Step 2 of every template calls TeamCreate(team_name: "...", ...). Do NOT check whether the tool exists first — just call it.
  2. If the call SUCCEEDS: continue with the template.
  3. If the call returns an ERROR or is unrecognized: STOP. Tell user: "Agent Teams requires CODEX_EXPERIMENTAL_AGENT_TEAMS=1 in settings.json. Team mode is not available."
  4. Do NOT fall back to subagents. $team MUST use Agent Teams or abort.
  5. All teammate spawns MUST include team_name parameter — never spawn Task without it.

When activated, IMMEDIATELY execute the matching template sequence below. Do NOT ask for confirmation. Do NOT explain what you're about to do. Execute the tool calls in order. Report progress after each major step.


CK Context Block

Every teammate spawn prompt MUST include this context at the end:

CK Context:
- Work dir: {CK_PROJECT_ROOT or CWD}
- Reports: {CK_REPORTS_PATH or "plans/reports/"}
- Plans: {CK_PLANS_PATH or "plans/"}
- Branch: {CK_GIT_BRANCH or current branch}
- Naming: {CK_NAME_PATTERN or "YYMMDD-HHMM"}
- Active plan: {CK_ACTIVE_PLAN or "none"}
- Commits: conventional (feat:, fix:, docs:, refactor:, test:, chore:)
- Refer to teammates by NAME, not agent ID

Read the full file on GitHub · 286 lines

Files

What ships with it

3 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.

  1. 2d ago First seen · 286 lines · 30 tokens per session scan A 8466b23b54d8

Subscribe to this mod's changes

ck:team is a skill published in the GitHub repository manhvann/codexkit (88 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 3,182 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

systematic-debugging

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

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens