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 YuDefine/nuxt-supabase-starter --skill bpgit 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/skills/yudefine/nuxt-supabase-starter/bp)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/bp"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/bp.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.02165 |
| Opus 5 | $0.00051 | $0.01082 |
| Sonnet 5 | $0.00021 | $0.00433 |
| Haiku 4.5 | $0.00010 | $0.00216 |
Grade A, and why
bp 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 today.
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.
bp — 最佳實踐落點路由
clade 有 7 種資產落點。分類負擔歸本 skill，不歸使用者——使用者只需要講出那條實踐是什麼，落點由這裡判、講出理由、等確認。
Mode dispatch
| Mode | 觸發 | 用途 |
|---|---|---|
record（預設） |
\bp <一句話>、「記成最佳實踐」 |
判落點 → 回報 → 等確認 → 落地 |
plan |
「新專案該套哪些現成標準」 | 依 stack 列出該套用的既有 convention |
check |
/bp check、commit gate 0-F 呼叫 |
對 staged diff 比對既有資產，防重造輪子 |
record
Step 1 — 判定 session 位置
| 目前在 | 做法 |
|---|---|
clade（~/offline/clade） |
直接往下走 |
| consumer | 這是 Direction B 跨界（consumer session → clade 改源頭 + 散播）。使用者送 \bp 就是明確授權，往下走；落地後 MUST 回到原 consumer 並明示已回來 |
Step 2 — 問三個問題
MUST 自己先答一遍，答不出來的才問使用者。目標是使用者回是非題，不是回「該放哪一層」。
| # | 問題 | 分支 |
|---|---|---|
| Q1 | 誰需要知道？ | 全 consumer → rules/core/／某類 stack → rules/modules/<group>/<variant>/／只有 clade → clade 自己的 .cursor/rules/local/（clade home 是 Claude session，這格是字面路徑不是投影）／只有某一個 consumer → 該 consumer 自己的 .clade/rules/ 或 tasks/lessons.md，不進 clade |
| Q2 | 何時需要知道？ | 每個 session → always-load rule／編輯特定檔時 → 帶 paths: 的 conditional rule／做特定任務時 → skill／查得到就好 → vendor/snippets/ 或 docs/ |
| Q3 | 它是什麼形態？ | 判準 → rule／操作步驟 → skill 或 snippet／可執行 → vendor/scripts/／成因與退場條件 → docs/rule-rationale/／失敗案例 → docs/pitfalls/／有 variant 與成熟度 → registry/conventions.json |
Q1 最後一支是不收的出口：\bp 送進來的實踐若只對一個 consumer 有效，落點在該 consumer 自家，不是 clade。證據只有一次 session 的觀察 → tasks/lessons.md；已演進成穩定規約 → 該 consumer .clade/rules/。NEVER 因為使用者送了 \bp 就一定要在 clade 找一個落點塞進去。
Q3 最後一支最常被漏掉：一條實踐若存在「推薦做法 vs 過渡做法」的分歧，它 MUST 進 registry/conventions.json——那是唯一機讀的最佳實踐目錄，沒進去的條目 plan 與 check 兩個 mode 都抓不到，等於登記了卻不會被套用。
Q2 / Q3 判到 docs/ 之後還有一層：docs/ 有 13 個子目錄，落哪一個以 docs/README.md 為 SoT——它定義各子目錄的准入 predicate、三組易混淆目錄的判準與掃描面契約，設計上就是給本 skill 判落點用的。判到 docs/ 就 MUST 讀它，NEVER 憑目錄名字猜，也 NEVER 把那些 predicate 複製進本檔（複本必漂移，正是該憲章 § 維護 要防的）。
What ships with it
1 file 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.
- today Changed · +3 lines 64b9e60569d6
- 4d ago First seen · 112 lines · 103 tokens per session scan A efc46b63e313
bp is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 2,165 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
agent-team-manager
A command-line manager for teams of AI agents, where each agent has a role and the team can use different workflows or models.
gh-issue
Size-audit, write, and split BanyanDB issues that somebody else or an automated TDD workflow can implement. Use whenever the user asks to file or revise an issue, decide whether an issue is too large, make an issue TDD-ready, turn a design into tickets, or split an umbrella into executable leaves. Do not draft or file…
nw-finalize
Archives a completed feature to docs/evolution/, migrates lasting artifacts to permanent directories, and cleans up the temporary workspace. Use after all implementation steps pass and mutation testing completes.
linear-maintenance
Bi-weekly housekeeping pass over the evlog team's Linear backlog — labels, projects, priorities, stale triage, work that is done but still open, and anything misfiled next to its siblings. Applies the mechanically verifiable fixes and surfaces the rest as decisions. Load this when the linear-maintenance schedule…
nw-jtbd-opportunity-scoring
JTBD opportunity scoring and prioritization - outcome statement format, opportunity algorithm, scoring interpretation, feature prioritization, and opportunity matrix template.
nw-jtbd-workflow-selection
JTBD workflow classification and routing - ODI two-phase framework, five job types with workflow sequences, baseline type selection, workflow anti-patterns, and common recipes.