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 agentmods add rules/lawofall/agentcore/prompt-designgit clone --depth 1 https://github.com/Lawofall/AgentCoreWhat 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 | $0.00602 | $0.00602 |
| Opus 5 | $0.00301 | $0.00301 |
| Sonnet 5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
prompt-design 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 2d 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
提示词改动
产品 AI 提示词（CEO 核 / 基座 / 队员身份 / 辩论 / Skill / 工具 schema / 事实层 / 场面门 / 引擎当场文案）先读再改：上下文工程 · 提示词设计原则。入场闸、一层一所有者、否决表权威在原则文，此处不重抄。
- 加一行只选一个落点 → 原则文新事故入场闸；加禁止句先定层再过补集测试。审议已有一句是否留在常驻 → 同一闸方向相反：先过「每回合都要用的身份？」；产品事实即使在
<身份>也出核。 - 一层一所有者：同一条纪律在提示串里只出现一次。标签 = 决策时刻（身份 / 输入 / 工作权威 / 诚实 / 输出），权威在原则文。基座不写
<身份>，只写 CEO 与 worker 同真的句子；工种不对称进角色<身份>或节点合同。HOW 在consult正文；when-to-use 在工具 description；目录行只写这是什么；闸在代码不进提示词。 - 禁止六类：补集禁止 / 判例入常驻 / 层放错 / 产品事实冒充身份 / 重复抄写 / 瘦身换闸 → 判据在原则文否决。
- 加闸 →
intercept-discipline.mdc，禁止用拦截补短提示。 - 注入字面出门过 现行信息：不改变以后行动的句子不留；废名连删，测试改缺席，禁止靠点名废字段「禁复活」。
体积：tests/test_ceo_core_ratchet.py（基座+核）、tests/test_tool_schema_size_ratchet.py（工具面）默认只降不升；test_prompt.py 守原则 / 缺席 / 唯一性，不守判例字面。
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.
- 2d ago First seen · 16 lines · 602 tokens per session scan A 0519fc21bcff
prompt-design is a cursor rule published in the GitHub repository Lawofall/AgentCore (78 stars, last pushed 3d ago), licensed MIT. It adds 602 tokens to every session, about $0.0030 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 2026-08-30.
Other cursor rules, from other repositories
project-overview
Core project architecture, patterns, and conventions for the AI Documentation Generator.
code-patterns
Python code style and recurring patterns (config, logging, errors, paths).
json-prompt-design
Protects MOTO prompt wording and defines cross-cutting JSON response invariants.
core-project-context
Canonical project context and ownership rules.
backend-python
Python and FastAPI standards for the backend.
dashboard-typescript
React and TypeScript standards for the operator dashboard.