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/qwenlm/qwen-code/loopnpx skills add QwenLM/qwen-code --skill loopgit clone --depth 1 https://github.com/QwenLM/qwen-codeWhat 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 | $0.00066 | $0.02444 |
| Opus 5 | $0.00033 | $0.01222 |
| Sonnet 5 | $0.00013 | $0.00489 |
| Haiku 4.5 | $0.00007 | $0.00244 |
Grade A, and why
loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/loop — run a prompt repeatedly
Subcommands
If the input (after stripping the /loop prefix) is exactly one of these keywords, run the subcommand instead of scheduling:
list— call CronList and display the results. Done.clear— call CronList, then call CronDelete for every job returned. Confirm how many were cancelled. Done.
Parsing
Parse the input after removing the /loop prefix:
- Empty input (no prompt, no interval): the autonomous path — run a self-paced autonomous loop. See the Autonomous mode section.
- Leading interval token: if the first whitespace-delimited token matches
^\d+[smhd]$(e.g.5m,2h), this is the fixed-interval recurring path. The rest is the prompt. - Trailing "every" clause: otherwise, if the input ends with
every <N><unit>orevery <N> <unit-word>(e.g.every 20m,every 5 minutes,every 2 hours), this is the fixed-interval recurring path. Extract that interval and strip it from the prompt. Only match when what follows "every" is a time expression —check every PRhas no interval. - Prompt-only input: otherwise, the entire input is the prompt and this is the prompt-only self-paced path.
If an interval was given but the prompt is empty (e.g. /loop 5m), this is a fixed-interval autonomous loop — see the Autonomous mode section.
Examples:
5m /babysit-prs→ fixed interval5m, prompt/babysit-prs(leading interval token)check the deploy every 20m→ fixed interval20m, promptcheck the deploy(trailing "every" clause)run tests every 5 minutes→ fixed interval5m, promptrun tests(trailing "every" clause)check every PR→ prompt-only self-paced path, promptcheck every PR("every" is not followed by a time expression)check the deploy→ prompt-only self-paced path, promptcheck the deploy- (empty) → self-paced autonomous loop (sentinel
<<autonomous-loop-dynamic>>) 5m→ fixed-interval autonomous loop (interval5m, sentinel<<autonomous-loop>>)
What ships with it
7 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.
- yesterday First seen · 115 lines · 66 tokens per session scan A fdccdc2f4de7
loop is a skill published in the GitHub repository QwenLM/qwen-code (27,507 stars, last pushed yesterday), licensed Apache-2.0. It adds 66 tokens to every session and 2,444 once invoked, about $0.0003 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
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
agent-manager-reference
Query agent-manager.dev's reference API and MCP server for documentation, the coding CLIs it manages, the tools its MCP server exposes, and the current release. Use instead of scraping the website's HTML.
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用；包含 AI Coding 事件表语义，以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE，通常与 sls-dashboard-builder 一起使用。.
novel-workshop
小说创作工作台。用户说写小说、创作小说、写故事、写穿越文、写言情、写科幻、创作故事、开始创作、继续写、写下一章、多视角、POV、装订成册时使用。AI-assisted novel writing workbench for outline, characters, chapter drafting, multi-POV narrative, editing, and book assembly.
hooksmith
Use when designing or reviewing safe Grok Build hooks for linting, tests, formatting, notifications, command guards, lifecycle automation, or project hook trust decisions.
repo-health-check
Use when auditing a repo before changes to find the smallest safe PR, quality risks, stale docs, missing tests, ignored-file gaps, or agent setup issues. Best first skill for unfamiliar codebases.