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 tzz123-hub/DevWhale --skill loop-budgetgit clone --depth 1 https://github.com/tzz123-hub/DevWhaleWrote 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/tzz123-hub/devwhale/loop-budget)<a href="https://agentmods.dev/skills/tzz123-hub/devwhale/loop-budget"><img src="https://agentmods.dev/badge/skills/tzz123-hub/devwhale/loop-budget/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/tzz123-hub/devwhale/loop-budget"><img src="https://agentmods.dev/badge/skills/tzz123-hub/devwhale/loop-budget.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00033 | $0.00398 |
| Opus 5.5 | $0.00013 | $0.00159 |
| Sonnet 5.5 | $0.00007 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
loop-budget 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 1mo 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
Loop Budget Guard（循环预算守卫）
在每次循环迭代的开始和结束时运行。
运行开始
- 读取
loop-budget.md获取每日上限和 kill-switch 标志。 - 读取
loop-run-log.md最近 24 小时的条目。 - 汇总当日该模式的
tokens_estimate。 - 如果花费 ≥ 模式每日上限的 80% → 仅报告模式（禁止子代理、禁止自动修复）。
- 如果花费 ≥ 100% 或
loop-pause-all已设置 → 立即退出，在 STATE.md 中写一行说明。 - 如果观察列表/状态中无可操作项 → 在 <5k token 内退出（不创建子代理）。
运行结束
向 loop-run-log.md 追加一条 JSON 对象：
{
"run_id": "<ISO8601>",
"pattern": "<pattern-id>",
"duration_s": <number>,
"items_found": <number>,
"actions_taken": <number>,
"escalations": <number>,
"tokens_estimate": <number>,
"outcome": "no-op | report-only | fix-proposed | escalated"
}
规则
- 绝不超出
loop-budget.md中max sub-agent spawns/run的限制。 - 高频模式（CI Sweeper、PR Babysitter）必须在无待办时提前退出。
- 自我节流时，在
loop-budget.md的 Alerts This Period 下追加一行。
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.
- 1mo ago First seen · 41 lines · 33 tokens per session scan A 9afa1314c99f
loop-budget is a skill published in the GitHub repository tzz123-hub/DevWhale (10 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 398 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
eac-desktop-tips
A quick reference for using and troubleshooting features in the Deepseek Harness EAC desktop client. It covers window behavior, conversation rollback, plugins, desktop pets, Skills, MCP services, updates, and logs.
electron-expert
Expert in Electron framework, desktop app development, IPC, and cross-platform packaging. Use when the user mentions desktop, Node.js, cross platform, Windows, macOS, or Linux, or when the task involves Electron Architecture, Process Types, IPC Communication, or App Lifecycle.
architecture-diagram
How to draw and maintain the architecture diagram Ensemblr keeps for a workspace — ensemblrgetarchitecturediagram to fetch the stored one (it answers with null when nobody has drawn this workspace yet), the IR shape, how to derive it from the codebase, and ensemblrupdatearchitecturediagram to store it. Read this when…
ensemblr
How Ensemblr works from inside it — the workspace/git-worktree model, the ensemblr control tools and what their answers mean, the committed .ensemblr/settings.toml (setup and run scripts, [git], [prompts], [infisical], environment variables), /.config/ensemblr/config.json, the Changes panel and diff comments, the…
lino-veusz-sci-plot
An automation guide for Veusz, a free scientific charting program similar to Origin, using Python scripts.
lino-local-vision
A local vision tool that uses a model running in LM Studio to inspect images and read text from them. It works through a local OpenAI-compatible service and is intended to run without sending images to an external API.