work-loop

work-loop is a skill for Claude Code, Codex from YuDefine/nuxt-supabase-starter. It costs 97 tokens per session (26,442 once invoked), scanned B, original, MIT.

An autonomous work loop for advancing repository to-do items, planned changes, handoffs, and technical debt. Technical debt is unfinished or overly costly code work that should eventually be improved.

In plain words
What is it for?
It scans for pending work, implements items it can decide itself, records progress and handoffs, and prepares concise decision options for items needing approval.
Why use it?
It keeps work moving across repeated runs and packages decisions that require human approval instead of silently skipping them.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/yudefine/nuxt-supabase-starter/work-loop
Any agent
npx skills add YuDefine/nuxt-supabase-starter --skill work-loop
Clone the repo
git clone --depth 1 https://github.com/YuDefine/nuxt-supabase-starter

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for work-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/work-loop.svg)](https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/work-loop)
Your own site
<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/work-loop"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/work-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 26,442 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00097 $0.26442
Opus 5 $0.00048 $0.13221
Sonnet 5 $0.00019 $0.05288
Haiku 4.5 $0.00010 $0.02644

Measured yesterday against content hash 97af2e960715, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

work-loop scanned grade B with 1 finding 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.

The scan reads SKILL.md. This mod also ships 1 executable file (runner.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

| `ls .claude/skills/wt` 存在,**或** `jq -r '.enabledPlugins' .claude/settings.json` 不是 `none` | 照上面三條走,扇出組 ≤4 in-flight |
template/.claude/skills/work-loop/SKILL.md · 924 lines

How it starts

The opening of the file, as written. The whole thing — 924 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/work-loop — 待辦自主推進迴圈

2026-08-05 由 /change-loop(含 --turbo)與 /handoff-loop 合併而成。舊名已移除,無相容 stub。

本 skill 是 loop 四型分類中的 proactive loop——trigger 交給 runner.sh/loop,工作清單交給 scan 自己找。四型分類與通用方法論見 cookbook vendor/snippets/loop-engineering/

沒有「走哪一支」的判定。 repo 有沒有 openspec/、待辦是 spectra change 還是 tech-debt 條目,都由 Step 2 的 scan 結果決定路由——無 openspec/ 的 repo 掃出來的 spectra 段就是空的,這是正常的,不是 scan 失敗

核心 contract:每次被叫起來,把待辦盡可能推到「已完成」「可驗收」或「已備妥決策選項」狀態。能自主決策的自主完成;必須人拍板的 NEVER 直接 skip——MUST 走 § Decision packaging 推進到「一句話就能答」的狀態。

Output contract:loop 的 output 是進度報告,不是 user call-to-action。

  • ✅ 「<change> 標 🟢 ready-for-review(寫入 HANDOFF)」「TD-317 已修並 commit a1b2c3d」— 報告事實
  • ✅ 「本輪處理 3 items:2 completed / 1 packaged。fingerprint 已變,續跑」— 報告進度
  • ❌ 「待 user 驗收:請執行 pnpm review:ui」— user call-to-action
  • ❌ 「待 user 決定:TD-402 要用 A 還是 B?」— 決策要落 awaiting[] + HANDOFF ## ⏳ Awaiting Charles,不是 chat 敘述(attended 下由 Step 2.7 用 AskUserQuestion 端出去問)
  • ❌ 「下一輪可推進:1. ... 2. ...」— 列選單讓 user 決定

Step 0 — Mode detection、lock、continuous invocation

$ARGUMENTS

Flags

  • --unattendedrunner.sh 每輪固定帶):5-item cap(避免 runaway)+ 禁止 AskUserQuestion。不帶時無 item cap,改由 Step 6 的 round cap / fingerprint 控制。

    裝載準則:cap 之內優先把同一 Location/同一 skill 的 item 併進同一輪。理由是成本不是整齊——runner 每輪起全新 process,而 git snapshot 每輪變動使 always-load 段整段重付一次冷載(約 90k effective tokens),輪數減半即該固定成本減半([[TD-433]],前提實測 median 18.6 分 < 1h cache TTL)。NEVER 反過來為了湊滿 5 個而把不相干的 item 拉進同一輪:cap 是上限不是配額,湊數只會讓單輪失敗牽連無關 item。

  • --runner-child(只由 runner.sh 帶):模型可見的 runner child 身分 marker;WORK_LOOP_RUNNER_CHILD=1 是同一身分的機械補強。

  • --linked-dispatch-mode foreground(只由 runner.sh 帶):runner child 內每一筆 decision-linked Pi dispatch 都是同輪 dependency,依 Step 1.5 的 foreground 契約執行;不帶時沿用一般 async watch protocol。

  • --min-wakeup-seconds <n>runner.sh 每輪固定帶,預設 1200;WORK_LOOP_MIN_WAKEUP_SECONDS 是機械補強):本輪每一個 ScheduleWakeup / Monitor 的 interval MUST ≥ n。帶了它就以它為準,NEVER 因為「這次只等一下下」用更短的值——短輪詢買不到 notification 沒給的東西(Step 0 § (d) 已逐字禁止輪詢進度)。不帶時各處原有的 interval 建議照舊。

  • 使用者說「自動推」「把待辦跑完」「持續做」「不要停」「無人值守」→ 等同要求 continuous(見下)。

Read the full file on GitHub · 924 lines

Changes

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.

  1. yesterday Changed 97af2e960715
  2. 4d ago First seen · 924 lines · 97 tokens per session scan B 47dd9d35ad1c

Subscribe to this mod's changes

work-loop is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 26,442 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

safe-sql-execution

Use whenever code will build, return, fetch, or execute SQL that runs against a user's real Postgres database — even when the request reads like an ordinary feature or bug fix and never says "security," "injection," or "SafeSqlFragment." This covers: writing or editing any pg-meta function, query builder, or endpoint…

supabase/supabase · 221 tokens

sdk-design

Doctrine for designing and evolving any SDK Grida ships — TypeScript, Rust, or otherwise. "SDK" here means a surface that crosses a foreign-or-foreign-treated boundary: published packages, separately-versioned consumers, FFI bindings, public-by-design modules. An SDK's job is to refuse; a strict, honest surface…

gridaco/grida · 199 tokens

create-evlog-map-rule

Add a new rule or a new framework adapter to evlog map in @evlog/cli. Use when adding a coverage check (requirement or opportunity) that scores entry points, or when extending the map scanner to a new framework. Covers rule source, registry, types, tests, docs, and the published skill.

HugoRCD/evlog · 74 tokens

markstream-svelte

Integrate the beta markstream-svelte package in Svelte 5 or SvelteKit apps. Use when Codex needs Svelte 5 runes, CSS and optional peers, smooth streaming, worker setup, renderer-local or scoped custom components, or SSR-safe boundaries. Svelte 4 is unsupported.

Simon-He95/markstream-vue · 67 tokens

map

高德地图路线规划与 POI 搜索。支持驾车、步行、骑行、公交路线规划,以及景点、餐厅搜索。当用户询问路线、行程规划、景点推荐、餐厅推荐时使用。.

countbot-ai/CountBot · 53 tokens

firebase-supabase-attack

Exploit Firebase/Supabase for data via JS config leak probe.

uphiago/recon-skills · 21 tokens