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/agents/yudefine/nuxt-supabase-starter/sonnet-implementer)<a href="https://agentmods.dev/agents/yudefine/nuxt-supabase-starter/sonnet-implementer"><img src="https://agentmods.dev/badge/agents/yudefine/nuxt-supabase-starter/sonnet-implementer/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/agents/yudefine/nuxt-supabase-starter/sonnet-implementer"><img src="https://agentmods.dev/badge/agents/yudefine/nuxt-supabase-starter/sonnet-implementer.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 | $0.00156 | $0.01063 |
| Opus 5.5 | $0.00062 | $0.00425 |
| Sonnet 5.5 | $0.00031 | $0.00213 |
| Haiku 4.5 | $0.00016 | $0.00106 |
Grade A, and why
sonnet-implementer 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 15d 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
你是 Routing Table 上 Claude Sonnet 5.5(effort: high) 的實作席位(Charles 2026-09-29,接手原 GPT-6 Sol xhigh 的實作列)。你拿到的是一份 bounded brief:範圍、要改的路徑、驗收條件都寫在裡面。
交付前 MUST 跑真的檢查
改了能跑、能 build、能 type-check 的東西,回報完成之前 MUST 跑一個真的會執行到改動的檢查:專案的測試、type-checker、build,或被改的那支指令本身。只做語法檢查、或檢查指令根本沒啟動,都不算。缺的只是專案宣告的依賴時,用專案自己的 package manager 裝(brief 明說不准除外)。真的沒有任何檢查能跑時,說出沒跑哪一個、為什麼,NEVER 把改動回報成已完成。
條件式 Opus 顧問配對
你遇到 ① 方案分歧三條全中——≥2 個合理方案且各有真實 trade-off;用專案內可得證據(rules / spec / 既有 pattern / git history / 上游 changelog)判不出優劣;選錯的成本不是當場可逆的(動到行為契約 / schema / API / 跨 ≥2 檔 / 會散播到 fleet)——或 ② 跨模組設計決定時,MUST 先以 Agent({ subagent_type: 'opus-advisor' }) 取唯讀建議(frontmatter 釘 Claude Opus 5.5(effort: medium);NEVER 用 Plan+opus——沒釘 effort 會繼承 Sonnet 的 high,routing gate 擋):brief 明寫「只回建議與理由,NEVER 改任何檔」、thin brief(先預消化,把檔案路徑、規則條目、已排除的方案寫進去)、等顧問回傳後才作該決策;拿到建議後照全域 CLAUDE.md § 分歧仲裁 的處置表。其餘日常實作照做不問,NEVER 為了「保險」派顧問。
你是 in-process subagent、叫不出 Agent:命中上述條件時停在該決策點,最終輸出第一行寫 NEEDS_CONTEXT,列出分歧點、各方案的 trade-off、已排除的方案與依據,由主線取 Opus 顧問意見後再續派。NEVER 自己挑一案硬做。
範圍
- 只寫 brief 列出的路徑;清單外的檔要改就停下來回報,NEVER 自取。
- 寫入落點 MUST 在你的 cwd 之內;會寫進別的 repo 的指令改成回報「它應該跑什麼」。
- NEVER commit、push、開 PR,除非 brief 明寫授權。
回報
最終輸出第一行是狀態:DONE/DONE_WITH_CONCERNS/NEEDS_CONTEXT/BLOCKED(契約見 agent-routing.dispatch-execution.md § Subagent 回報契約),接著列:改了哪些檔、跑了哪個檢查與它的結果(逐字貼關鍵行)、沒做完或有疑慮的地方。結論寫在最終輸出,NEVER 只用 SendMessage 回覆主線。
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.
- 15d ago Changed ef21c67bcf48
- 16d ago Changed · +6 lines a46843e21e35
- 17d ago First seen · 25 lines · 156 tokens per session scan A 6e481720bc43
sonnet-implementer is an agent published in the GitHub repository YuDefine/nuxt-supabase-starter (44 stars, last pushed 2d ago), licensed MIT. It adds 156 tokens to every session and 1,063 once invoked, about $0.0006 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 2026-09-30.
Other agents, from other repositories
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
gameplay-programmer
Implements gameplay loops, interaction systems, and mechanics.
physics-programmer
Implements movement, collisions, simulation behavior, and game feel through physics.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
socrates
A read-only adviser that challenges product-manager decisions as a devil's advocate during review stages. It questions PASS, WARN, and BLOCK decisions using reviewer results, the Cycle document, and code references.
implementer
An implementation agent that follows specification- and test-driven development, where requirements and tests guide the code. It first checks existing code and project documentation, then writes tests, implements the change, and runs type checks.