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.
git clone --depth 1 https://github.com/YuDefine/nuxt-supabase-starterWrote 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/rules/yudefine/nuxt-supabase-starter/session-tasks.operations)<a href="https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/session-tasks.operations"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/session-tasks.operations.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 5.1 | $0.00000 | $0.14822 |
| Opus 5 | $0.00000 | $0.07411 |
| Sonnet 5 | $0.00000 | $0.02964 |
| Haiku 4.5 | $0.00000 | $0.01482 |
Grade A, and why
session-tasks.operations 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 — 615 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Tasks — 操作細節
觸發條件、檔名格式、禁令在 always-load 的 [[session-tasks]]（本檔是它的操作展開，首次觸碰 tasks/** 後自動載入）。
核心命題：spectra change 流程（propose → apply → archive）適合大型結構化變更；ad-hoc 小工作（debug、配置調整、單檔 fix、勘查）需要更輕量的 todo 機制。但若用全域單檔（如 tasks/todo.md）作為共享 working memory，multi-session 並行時會 lost update 或互相覆蓋清理結果。以 per-session 分檔 解決，並強制升級路徑避免長期堆積。
何時用 tasks/，何時不用
| 工作類型 | 應該放哪 | 理由 |
|---|---|---|
| 明示唯讀／禁止寫檔，或只要對話中的盤點／計畫 | 對話中的進度與交付 | 寫 task 檔或 spine 不在任務範圍 |
| 只允許指定計畫／報告文件 | 該指定文件 | 單一產物承載進度，不另外擴充寫入範圍 |
| 大型結構化變更（涉及 spec、跨多檔、跨層、需要 design review） | spectra change（openspec/changes/） |
走完整 propose → apply → archive 流程 |
| 已授權本機修改的 ad-hoc 小工作（單一 debug、配置調整、單檔 fix） | tasks/<id>.md |
比 spectra 輕一個量級 |
| 跨 session WIP 交接 | HANDOFF.md |
session 結束時的「信件」 |
| 中長期未來工作（不在當前 change scope） | openspec/ROADMAP.md ## Next Moves |
排優先序的未來 backlog |
| 範圍外技術債 / 未解決項長期追蹤 | docs/tech-debt.md（TD-NNN） |
永續 register |
| 不需要追蹤的單一 prompt | 都不需要 | 直接做完即可 |
判斷準則：先按當次授權套用 [[session-tasks]] 的載體表；已允許本機修改而不確定追蹤形式時，先用 tasks/<id>.md。發現規模膨脹（要動 spec、要 design review、要跨多檔）時，依專案既有 workflow 升級追蹤；追蹤形式不擴大實作或發布授權。
檔案結構
tasks/
<YYYY-MM-DD-HHMM>-<slug>.md ← 一 session 一檔，當前進行中
archive/
<YYYY-MM-DD-HHMM>-<slug>.md ← 已完成或已升級的舊檔（git history 已留證，可直接刪）
lessons.md ← 維持單檔（被糾正才寫，撞檔機率極低）
tasks/ 是 tracked（不進 .gitignore）——「刪檔 = git history 留證」的前提就是它被追蹤過。archive/ 可定期整批刪。
建檔的同一步順路鑄 work id（MUST）
建完 tasks 檔的同一步 MUST 讓這件事在 /board 上有名字：
node ~/offline/clade/vendor/scripts/flow/flow.ts open <slug> \
--actor claude-code --origin 'tasks:tasks/<檔名>' --title '<一句話：這件事是什麼>'
# stderr 印出 export CLADE_WORK_ID=W-<date>-<slug>；本 session 後續的 dispatch 沿用它，
# relay / fanout 的 successor 也會繼承，整條接力鏈算同一件事。
每一個新建的 tasks 檔都鑄，不是只有覺得會做很久的那次——「這件事夠不夠大」這個判斷本身
正是 79% 事件掛在 orphan- 名下的成因（clade 2026-08-27 實測）。
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 Changed · +31 lines d673c68cb90b
- 3d ago First seen · 584 lines · 0 tokens per session scan A 3b72c557a6f1
session-tasks.operations is a cursor rule published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 14,822 tokens. 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 2026-09-03.
Other cursor rules, from other repositories
ai-assisted-performance-review
Evaluate performance fairly when output is AI-assisted — what still measures the human, what now measures the tooling, and how to run the review conversation. Use when reviewing someone whose work is heavily AI-assisted, when output volume stopped meaning anything, when calibrating a team with uneven AI adoption, or…
revenue-architect
The local environment is optimized with rtk (Rust Token Killer). Always use the rtk prefix for shell commands (e.g., rtk npm test) to minimize token consumption.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.