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 agentmods add skills/techymt/claude-code-superpowers/task-systemnpx skills add TechyMT/claude-code-superpowers --skill task-systemgit clone --depth 1 https://github.com/TechyMT/claude-code-superpowersWhat 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 | $0.00097 | $0.01885 |
| Opus 5 | $0.00048 | $0.00942 |
| Sonnet 5 | $0.00019 | $0.00377 |
| Haiku 4.5 | $0.00010 | $0.00188 |
Grade A, and why
task-system 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 yesterday.
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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task System
The pattern
A Task is a unit of background work that runs independently of the main conversation loop. Tasks are spawned by tools or commands, tracked in AppState.tasks by ID, write their output to a disk file (not memory), and progress through a lifecycle: pending → running → completed | failed | killed.
The key design: tasks do not block the conversation. After a task is spawned, the LLM can continue the conversation, ask the user for more input, or respond to the task's output when it's done. The user can check task status with /tasks, kill a task with /tasks kill, or watch its output live.
Why this matters
Some operations take seconds to minutes: running a test suite, compiling a large project, cloning a repository, running a long Temporal workflow. If these blocked the conversation loop, the user would be stuck waiting. The Task system decouples the spawn from the wait.
Disk-backed output (each task writes to a temp file, tracked by outputFile + outputOffset) is a deliberate choice over in-memory buffers. It means: (1) output is preserved across session restarts; (2) the output file can be tail -f'd externally; (3) the main process doesn't hold all output in memory; (4) partial output can be read back at any offset without re-running the task.
How to apply it
- To spawn a task: use the
TaskCreateToolfrom the tool registry. It accepts atype,description, and type-specific configuration. The tool returns ataskId. - The task lifecycle is managed by the task runner for its type (e.g.,
LocalAgentTask,LocalShellTask). Don't manage it manually. - To read task status: use
context.getAppState().tasks[taskId]— it returns aTaskStateBasewithstatus,outputFile,outputOffset, and timing. - To kill a task: use
TaskStopToolwith thetaskId. - To stream output: read from
outputFilestarting atoutputOffset— increment the offset with each read. - When the task completes, set
endTimeand updatestatusto'completed'or'failed'viasetAppState.
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.
- yesterday First seen · 192 lines · 97 tokens per session scan A f1b7cb0c75ac
task-system is a skill published in the GitHub repository TechyMT/claude-code-superpowers (5 stars, last pushed 5mo ago), licensed MIT. It adds 97 tokens to every session and 1,885 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.