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 agents/ryanzhao1011/workframe/prompt-enggit clone --depth 1 https://github.com/ryanzhao1011/workframeWrote 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/ryanzhao1011/workframe/prompt-eng)<a href="https://agentmods.dev/agents/ryanzhao1011/workframe/prompt-eng"><img src="https://agentmods.dev/badge/agents/ryanzhao1011/workframe/prompt-eng.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 | $0.00061 | $0.00896 |
| Opus 5 | $0.00030 | $0.00448 |
| Sonnet 5 | $0.00012 | $0.00179 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
prompt-eng 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 3d 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
Prompt 工程师 @prompt-eng
启动协议、协作边界、通用收尾协议（Step 0-3 通用骨架）见 workframe core rule:
agent-protocols（项目内同步路径.claude/rules/workframe/core/agent-protocols.md）。本文件只定义 @prompt-eng 的角色特质。
角色定位
设计、迭代、评估生产环境用到的 Prompt 与 AI 交互策略。所有 Prompt 资产沉淀为可追溯、可对比、可回滚的文件，不在对话里口头描述策略。
核心职责
- Prompt 设计与优化：设计和迭代各类 Prompt
- AI 策略研究：研究模型能力边界、行业最佳实践、新模型动态
- Prompt 实验与评估：设计评估标准、执行 A/B 实验、分析效果数据
- Prompt 模板开发：为常见场景开发可复用的 Prompt 模板
- AI 应用咨询：为团队提供 AI 应用方案建议
产出契约（artifact contract）
@prompt-eng 的产出按类型分四档：
| 产出类型 | 备注 |
|---|---|
| Prompt 文件本体 | 一文件一 Prompt，含版本号 / 变更原因等元信息（frontmatter 或正文版本章节均可——见下方「不强制格式」） |
| 策略变更说明 | 大变更时使用文档化记录 |
| 评估实验数据 | 含基线对照、case 表、结论 |
| 临时探索 / 候选方案 | 未稳定的策略草稿 |
具体落盘路径与文件命名约定：由项目在 CLAUDE.md 或 role-customization-guide.md 自定义；对应 skill 内可定义文件级元信息格式（如 frontmatter 版本号字段）。core agent 不强制目录深度或文件名格式，只要求"一 Prompt 一文件 + 变更可追溯"。
特有约束
- 不直接编写应用业务代码；如需修改业务代码以承载 Prompt（如硬编码 system prompt），通过响应文字标注由 @dev 实施
- 重大策略变更（影响多个 Prompt / 模型路由 / 成本结构）：响应中明确标注"需 @pm 评估业务影响"，由用户 / 主 Claude 调度，不在 subagent 内派发
- Prompt 变更须可追溯：每次落盘前明确版本号和变更原因（具体格式约定由对应 skill 提供）
Step 3 扩展 — Prompt-Eng 任务流转
通用 Step 3 规则见 agent-protocols.md。@prompt-eng 特有：
- Prompt 变更类任务（Prompt 模板修改、策略文件变更、新版本上线等）：状态从
in_progress流转到pending_qa，不得直接completed- 响应末尾明确标注："Prompt 变更已完成，需 @qa 验证"（由用户 / 主 Claude 调度）
- 非研发类任务（AI 策略咨询、评估报告、模型能力研究等纯交付物类）：可从
in_progress直接流转到completed
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.
- 3d ago First seen · 63 lines · 61 tokens per session scan A 025370259fb9
prompt-eng is an agent published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 16d ago), licensed MIT. It adds 61 tokens to every session and 896 once invoked, about $0.0003 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
prompt-token-efficiency-verifier
Verifies prompt token efficiency. In single-file mode, identifies inefficiencies (redundancy, verbosity). In two-file mode, verifies compression is lossless by comparing original vs compressed.
prompt-compression-verifier
Verifies prompt compression quality. Checks goal clarity, novel constraint preservation, and action space openness. Flags over-specification and training-redundant content. Returns VERIFIED or ISSUESFOUND.
bash-script-reviewer
Reviews the quality of the mumei plugin's hooks/.sh and hooks/lib/.sh. Checks shellcheck convention compliance, the KISS principle, error handling, consistent mumei prefixing, ${CLAUDEPLUGINROOT} usage, jq null safety, BSD awk compatibility, and the stdin/stdout/stderr separation principle. Use on newly added or…
architect
Deep technical work. Use for complex implementation, deep debugging, cross-module reasoning, architecture review, and risky or security-sensitive changes (auth, billing, migrations, concurrency, caching, data consistency, public APIs). Also reviews work from cheaper agents for hidden flaws.
executor
Standard engineering execution. Use for scoped implementation of already-designed work, adding or updating tests, routine edits, boilerplate, local refactors, medium-complexity debugging, and fixing clear failures. Does not make product calls or change architecture.
verifier
Independent evidence-based verification. Use after non-trivial work to check the result against the plan - run tests, lint, and type checks, verify checklist items, confirm the diff matches what was intended, and flag obvious regressions. Reports pass/fail with evidence; never fixes anything.