vibe-async-task-queue

A persistent task list for useful work that is not blocking the current task and should be handled later, including in another session. Tasks are stored in a project-specific JSON file.

In plain words
What is it for?
Use it to record documentation updates, non-critical flaky tests, review findings, or other follow-up work that is not already tracked in an issue tracker.
Why use it?
It prevents non-urgent work from being forgotten when it is deferred. It also turns informal TODO notes and minor review findings into trackable tasks with context and completion conditions.

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/mracal/vibe-engineering/async-task-queue
Any agent
npx skills add mracal/vibe-engineering --skill async-task-queue
Clone the repo
git clone --depth 1 https://github.com/mracal/vibe-engineering

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 602 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00035 $0.00602
Opus 5 $0.00017 $0.00301
Sonnet 5 $0.00007 $0.00120
Haiku 4.5 $0.00003 $0.00060

Measured 2d ago against content hash 1942ed706929, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibe-async-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 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.

Origin

This is a copy

100% identical to vibe-async-task-queue — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/async-task-queue/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vibe-async-task-queue

Not everything needs to be done right now. But "I'll do it later" only works if "later" actually happens.

When to Use This Skill

  • You identify work that should be done but isn't blocking the current task
  • During code review, you find issues that aren't urgent
  • Tests reveal non-critical flakiness
  • Documentation needs updating but not right now
  • "TODO" comments that should become tracked tasks

When NOT to Use This Skill

  • Blocking work that must be done now
  • Tasks already tracked in an issue tracker (GitHub Issues, Jira, etc.)
  • One-off tasks in the current session (just do them)

Queue Format

Tasks are stored in a JSON file at a project-specific location (e.g., .claude/task-queue.json):

{
  "tasks": [
    {
      "id": "vibe-001",
      "created": "2026-02-28",
      "priority": "medium",
      "status": "pending",
      "description": "Add error handling to parseConfig edge cases",
      "target_files": ["internal/config/parser.go"],
      "acceptance": "go test ./internal/config/... -run TestParseConfigEdge -v passes",
      "context": "Discovered during fuzz testing session"
    }
  ]
}

Steps

Adding a Task

  1. Identify the work
  2. Write a clear description with:
    • What needs to be done
    • Which files are affected
    • How to verify it's done (acceptance command)
    • Why it was deferred (context)
  3. Append to queue file

Processing the Queue

  1. Read queue file
  2. Pick highest-priority pending task
  3. Set status to in_progress
  4. Do the work
  5. Run acceptance test
  6. If pass: set status to completed, commit
  7. If fail: set status to pending, add notes about what went wrong

Reviewing the Queue

List all tasks with status counts. Identify stale tasks (>7 days pending).

Output Format

Task Queue Status

Pending: X | In Progress: Y | Completed: Z | Failed: W

ID Priority Description Age Status
vibe-001 high Add auth token refresh 2d pending
vibe-002 medium Fix flaky test in utils 5d pending

Read the full file on GitHub · 82 lines

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 · 82 lines · 35 tokens per session scan A 1942ed706929

Subscribe to this mod's changes

vibe-async-task-queue is a skill published in the GitHub repository mracal/vibe-engineering (3 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 602 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to vibe-async-task-queue, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

moai-kanban-foreman

One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…

modu-ai/moai-adk · 76 tokens

sprint-planning

Plan implementation sprints with story selection, goal definition, and execution ordering.

a5c-ai/babysitter · 0 tokens

kanban-management

Initialize and manage Kanban board state for feature workflow tracking.

a5c-ai/babysitter · 0 tokens

moai-workflow-project

Integrated project management system covering documentation, language initialization, template optimization, docs generation, and JIT document loading. Absorbed from moai-workflow-templates, moai-docs-generation, and moai-workflow-jit-docs.

modu-ai/moai-adk · 55 tokens

cross-source-correlation

Correlate near-in-time events across PR merges, deploys, monitoring (Sentry/NewRelic/Datadog/AppDynamics) and ticket trackers (Jira/Azure DevOps) into confidence-scored clusters that answer "which deploy caused this bug" without manual tab-switching.

aozyildirim/Agena · 64 tokens

review-backlog-killer

Detect pull requests aging past warn / critical thresholds, score severity, and nudge reviewers via Slack DM, channel, email, or directly as a PR comment — with one-time auto-escalation when a PR hits critical so velocity stops leaking through review queues.

aozyildirim/Agena · 58 tokens