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/vectie/moonclaw/provider-task-executionnpx skills add vectie/moonclaw --skill provider-task-executiongit clone --depth 1 https://github.com/vectie/moonclawWrote 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/vectie/moonclaw/provider-task-execution)<a href="https://agentmods.dev/skills/vectie/moonclaw/provider-task-execution"><img src="https://agentmods.dev/badge/skills/vectie/moonclaw/provider-task-execution.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.00257 |
| Opus 5 | $0.00015 | $0.00129 |
| Sonnet 5 | $0.00006 | $0.00051 |
| Haiku 4.5 | $0.00003 | $0.00026 |
Grade A, and why
provider-task-execution 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 4d 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.
What it actually says
Provider Task Execution
Use this skill when MoonClaw delegates work to a domain-local provider boundary.
Goal
Do the task inside the provider workspace and report what actually changed.
Rules
- Do not return plans, outlines, checklists, or commentary about what you intend to do.
- Use the listed skill files, policy, routines, pages, and memory as the work method.
- Produce durable outputs when the task requires durable book updates.
- If durable outputs were created, list them as artifact paths relative to the workspace.
- Only emit memory candidates that are worth persisting back into the provider boundary.
- If the task cannot produce durable outputs yet, return a concrete blocker summary and say what is missing.
- Do not pretend the task succeeded when no durable work happened.
Durable-output expectations
- Prefer concrete source, entity, concept, query, synthesis, or other domain pages over vague completion text.
- If nothing durable was created, say so explicitly and explain why.
Output discipline
- Return JSON only.
- Follow the exact runtime contract supplied by MoonClaw.
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.
- 4d ago First seen · 33 lines · 30 tokens per session scan A 968fa6dccc38
provider-task-execution is a skill published in the GitHub repository vectie/moonclaw (24 stars, last pushed 11d ago), licensed Apache-2.0. It adds 30 tokens to every session and 257 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 2026-08-30.
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…