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 patrick-fu/awesome-skills --skill long-task-controlgit clone --depth 1 https://github.com/patrick-fu/awesome-skillsWrote 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/patrick-fu/awesome-skills/long-task-control)<a href="https://agentmods.dev/skills/patrick-fu/awesome-skills/long-task-control"><img src="https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/long-task-control/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/patrick-fu/awesome-skills/long-task-control"><img src="https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/long-task-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.00743 |
| Opus 5.5 | $0.00016 | $0.00297 |
| Sonnet 5.5 | $0.00008 | $0.00149 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
long-task-control 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 18d 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.
Long Task Control
Preserve verified work while correcting the course. Constrain acceptance and ownership; leave execution tactics free. This workflow needs no other skill.
Target
Reconstruct the outcome, scope and acceptance criteria from the original request and later authorized changes. Newer authorized intent wins; expose unresolved conflicts. Compare the work against this target at each major phase boundary.
Observe
Inspect artifacts, commands, checks and delegate state directly. Separate liveness, progress toward the target and verified completion. Silence, elapsed time, an active process or a dirty diff alone establishes neither progress nor failure. Useful diagnosis and necessary preparation count as progress before acceptance checks finish.
Wait for a meaningful checkpoint while work advances or a known dependency is pending. A missed checkpoint prompts targeted diagnosis, not automatic replacement. Repeated failures without changed conditions, a new hypothesis or diagnostic information call for a new route. Preserve accepted work; stop the unproductive attempts, not the overall task.
Challenge
Default to separate, clean-context, read-only reviewers at major phase boundaries. Challenge Design (soundness, ROI, gold-plating) and Drift (intent, progress, evidence, stale work). Reviewers form their findings independently before reconciliation. Complete contract-changing review before dependent writing; non-blocking review may run concurrently.
Give one owner the findings: deduplicate, check the evidence, resolve conflicts and classify actionable defects, boundary notes, overdesign and false positives. Explain material findings with concrete evidence. Separate review and repair ownership. Re-review material repairs. At closure, run both lenses twice over the entire cumulative delivery; preserve any stronger requested review cadence. Report unavailable independence or incomplete required rounds as review gaps.
Correct
Disposition material findings: keep, prune, repair, replan or escalate. Break remaining work into independently verifiable outcomes. Preserve useful context and artifacts while retiring stale work and its descendants.
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.
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.
- 18d ago Changed · -5 lines 279605e49b4e
- 1mo ago First seen · 90 lines · 41 tokens per session scan A 0e87cd13a1ed
long-task-control is a skill published in the GitHub repository patrick-fu/awesome-skills (69 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 743 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…