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/elct9620/claude-powerloop-plugin/powerloopnpx skills add elct9620/claude-powerloop-plugin --skill powerloopgit clone --depth 1 https://github.com/elct9620/claude-powerloop-pluginWhat 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 | $0.00081 | $0.03837 |
| Opus 5 | $0.00041 | $0.01919 |
| Sonnet 5 | $0.00016 | $0.00767 |
| Haiku 4.5 | $0.00008 | $0.00384 |
Grade A, and why
powerloop 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.
How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
powerloop — Structured Loop with Quality Phases
An enhanced /loop that wraps recurring tasks in a Plan → Execute → Review → Sample cycle. Track progress per item, dispatch work to SubAgents, and auto-stop when quality sampling passes.
Interactive Setup Flow
When invoked, guide the user through these questions in order. Adapt phrasing naturally — do not dump all questions at once.
Step 1: Goal
Ask what the user wants to accomplish. Examples:
- "Refactor all UI components"
- "Implement remaining features from SPEC.md"
- "Convert all class components to function components"
Rephrasing for clarity is fine, but do not drop qualifiers, scope constraints, or edge-case notes — these details affect how SubAgents make judgment calls later. If you need to condense, confirm the rewritten goal with the user before proceeding.
Derive a short lowercase identifier from the goal for the progress file name (e.g., refactor, spec-impl, migrate).
Step 2: Execution Approach
Ask what skills or commands to use during the Execute phase. Examples:
/coding:write→/coding:review→/coding:refactor/coding:fixfor each item- Custom instructions
Step 3: Review Approach
Ask what skills or commands to use during Review and Sample phases. Examples:
/coding:review→/coding:refactor/coding:testingto verify tests pass- Custom review criteria
Step 4: Interval
Ask the preferred interval between executions. Suggest 5m as default. Support the same format as /loop: Ns, Nm, Nh, Nd.
Step 5: Sample Configuration
Ask whether to enable the Sample phase and the pass target:
- Default: enabled, 10 passes required
- Allow customization: "How many consecutive passes required? (default: 10)"
- Allow disabling: if the user only wants Plan → Execute → Review (auto-stop after Review completes; set
sample_passes: 0/0in frontmatter)
Step 6: Language
Ask the user's preferred language for note content (progress table items, log entries, notes). Default: English. Preserve the user's original goal text in frontmatter without translation regardless of this setting.
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.
- 2d ago First seen · 248 lines · 81 tokens per session scan A 8f2f052a3476
powerloop is a skill published in the GitHub repository elct9620/claude-powerloop-plugin (7 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 3,837 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…