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 task-queuegit 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/task-queue)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/task-queue"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/task-queue/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/task-queue"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/task-queue.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 | $0.00039 | $0.00764 |
| Opus 5 | $0.00019 | $0.00382 |
| Sonnet 5 | $0.00008 | $0.00153 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
mk:task-queue 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Queue & Ownership Tracker
Manages task assignment and file ownership during parallel execution.
Task Queue
Tasks are tracked in session-state/task-queue.json:
{
"tasks": [
{
"id": 1,
"description": "Implement API endpoints",
"owner": null,
"status": "pending",
"ownership": ["src/api/*", "src/routes/*"],
"blocked_by": []
},
{
"id": 2,
"description": "Implement UI components",
"owner": null,
"status": "pending",
"ownership": ["src/components/*", "src/pages/*"],
"blocked_by": []
}
]
}
Task Lifecycle
pending → claimed (agent assigned) → in_progress → completed
→ blocked (dependency not met)
Claiming Protocol
- Agent requests next available task
- Queue returns lowest-ID task where:
status=pendingANDblocked_byall completed - Agent declares ownership globs
- Queue checks for overlap with other in_progress tasks
- If overlap: REJECT claim, report conflict to orchestrator
- If no overlap: ASSIGN task, set
status=in_progress, recordowner
Ownership Enforcement
Each task declares file ownership via glob patterns. Before any file write, check if the file matches the agent's declared ownership.
| Action | Owned File? | Result |
|---|---|---|
| Read | Any | Always allowed |
| Write/Edit | Owned | Allowed |
| Write/Edit | Not owned | STOP — report ownership violation |
| Write/Edit | Overlapping | STOP — report conflict to orchestrator |
Integration
- Orchestrator creates the task queue when decomposing parallel work
- Parallel agents claim and complete tasks
- Orchestrator monitors queue for completion and triggers integration test
- Queue is ephemeral (session-state/) — recreated per parallel execution
Team Coordination
Team-mode coordination rules (file ownership, commit discipline, completion messages) live
in .claude/skills/team-config/references/team-coordination.md, loaded by mk:team-config
on team activation.
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 · 97 lines · 39 tokens per session scan A 0731b3a5bc0d
mk:task-queue is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 764 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 2026-09-03.
Other skills, from other repositories
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.
plan
Plan features spanning multiple domains: billing (Stripe), auth (RBAC), real-time (Presence), webhooks, jobs (Oban). Use when designing interconnected systems or converting review findings into tasks.
work
Execute Elixir/Phoenix plan tasks with progress tracking. Use after /phx:plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.
phx-deps-update
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).
rfi-management
Complete RFI (Request for Information) management system. Create, track, route, and analyze RFIs with automatic notifications and response deadline tracking.
daily-report-generator
Automatically generate daily construction reports from field data, worker inputs, weather, and progress photos. Creates professional PDF reports.