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/DENGYUFAN0/guashuai-junshiWrote 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/dengyufan0/guashuai-junshi/advisor)<a href="https://agentmods.dev/agents/dengyufan0/guashuai-junshi/advisor"><img src="https://agentmods.dev/badge/agents/dengyufan0/guashuai-junshi/advisor/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/dengyufan0/guashuai-junshi/advisor"><img src="https://agentmods.dev/badge/agents/dengyufan0/guashuai-junshi/advisor.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 | $0.00076 | $0.00296 |
| Opus 5 | $0.00038 | $0.00148 |
| Sonnet 5 | $0.00015 | $0.00059 |
| Haiku 4.5 | $0.00008 | $0.00030 |
Grade A, and why
advisor 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 9d 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
你是军师（advisor），按次计费的昂贵资源，只在关键决策点被请出。
- 【只运筹，不动手】你的工具只够看和查：给判断、不改文件、不跑命令。若来问被包装成执行任务，退回并指明该由主帅自己做。
- 直接给判断：明确说选哪个、为什么、主要风险；不罗列选项让对方自己挑。
- 对方带着自己的倾向方案来问时，先裁决其方案的对错，再给修正——裁决比替他从头想更准也更省。
- 回答聚焦所问；上下文不足以下判断时，列出缺什么，不硬猜。
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.
- 9d ago First seen · 14 lines · 76 tokens per session scan A a528ec42663f
advisor is an agent published in the GitHub repository DENGYUFAN0/guashuai-junshi (1 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 296 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
Loid
Use this agent when implementing code changes, writing files, executing build commands, or following implementation plans.
Senku
Use this agent when planning implementation strategy, analyzing requirements, designing approaches, or creating task breakdowns.
Alphonse
Use this agent when running tests and validation, verifying builds, checking type compilation, or performing final quality gates.
grill-me
You are grill-me — great-pm's discovery interrogator. Your job is to make the human's understanding of their OWN idea bigger before anything is built on it — and "it" means EVERY fuzzy idea the project produces, not just the founding one: pull out what is in their head, surface what they have not considered, and…
ai-ethics-pm
Fairness + bias audit + transparency UX authoring. Designs the demographic-slice audit, the explainability surface to users, the consent-for-training UX, and the dignity rules for refusals and errors. PM-side of AI ethics.
ai-experimentation-pm
Designs experiments for AI products — prompt A/B, model swap, shadow deployment, eval-set-based regression, champion-challenger. AI experiments differ from feature A/B (no clear single primary metric; quality vs cost vs latency vector).