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.
npx skills add ngocsangyem/MeowKit --skill team-configgit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ngocsangyem/meowkit/team-config)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/team-config"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/team-config/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/team-config"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/team-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00061 | $0.00784 |
| Opus 5 | $0.00030 | $0.00392 |
| Sonnet 5 | $0.00012 | $0.00157 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
mk:team-config 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Configuration
Sets up the infrastructure for parallel agent execution. Called by orchestrator when a COMPLEX task is decomposed into independent subtasks.
What It Does
- Analyzes the task — identifies independent subtasks from the plan
- Generates ownership map — assigns file ownership globs per subtask
- Creates worktrees — one git worktree per parallel agent
- Initializes task queue —
session-state/task-queue.jsonwith claiming protocol - Validates no overlap — checks ownership globs for conflicts before starting
Setup Flow
Plan approved (Gate 1)
↓
Orchestrator identifies parallel opportunity
↓
mk:team-config
├── 1. Parse plan for independent subtasks
├── 2. Generate ownership map (which agent owns which files)
├── 3. Validate zero overlap between ownerships
├── 4. Create git worktrees via mk:worktree
└── 5. Create task-queue.json via mk:task-queue
↓
Parallel agents start claiming tasks
Team Coordination Rules
When team mode activates, Read references/team-coordination.md — the team-only
coordination rules (file ownership per task, no force-push, worktree-branch commits,
actionable completion messages, lead docs-impact ownership). These were moved out of
always-loaded parallel-execution-rules.md so they load only on team activation.
Ownership Map Template
See templates/ownership-map-template.md for the format agents use to declare file ownership.
Constraints
- Max 3 parallel agents (from
parallel-execution-rules.md) - Only COMPLEX tasks qualify (orchestrator enforces this)
- Gates (1 and 2) are never parallelized
- All worktrees branch from current feature branch HEAD
Gotchas
- Overlapping ownership kills parallelism — if two subtasks need the same file, they can't be parallel. Restructure the decomposition or handle the shared file in a sequential pre-step
- Worktree naming with special characters — skill names with
:(e.g.,mk:review) need quoting in shell paths - Stale worktrees from crashed sessions — run
git worktree listto check for orphaned worktrees before creating new ones - Integration test is mandatory — after merging all worktrees, the full test suite MUST pass. Don't skip this
What ships with it
2 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.
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.
- 9d ago First seen · 85 lines · 61 tokens per session scan A b38b8812407b
mk:team-config is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 784 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
release
CONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release. Use when shipping a new plugin version. NOT distributed.
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
watch-pr
Watch an Elixir/Phoenix PR with an Amp Orb keep-alive lease until required non-deployment CI is green and review threads are resolved. Use after opening or updating a PR.
git-pushing
Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests.