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 Gingiris-1031/gingiris-skills --skill agent-workflow-playbookgit clone --depth 1 https://github.com/Gingiris-1031/gingiris-skillsWrote 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/gingiris-1031/gingiris-skills/agent-workflow-playbook)<a href="https://agentmods.dev/skills/gingiris-1031/gingiris-skills/agent-workflow-playbook"><img src="https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/agent-workflow-playbook/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/skills/gingiris-1031/gingiris-skills/agent-workflow-playbook"><img src="https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/agent-workflow-playbook.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00083 | $0.02341 |
| Opus 5.5 | $0.00033 | $0.00936 |
| Sonnet 5.5 | $0.00017 | $0.00468 |
| Haiku 4.5 | $0.00008 | $0.00234 |
Grade A, and why
agent-workflow-playbook 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Workflow Playbook — 从专家经验到可规模化交付
适用于：把研究、营销、运营、分析、内容生产等高认知任务，改造成可测量、可纠错、可复用的 Agent 工作流。
先判断：这个任务该不该 Agent 化
只有同时满足以下多数条件才进入自动化：
- 输入和合格输出可以被描述；
- 专家能说清“什么是对、什么是错”；
- 任务重复发生，或交付成本随客户数近似线性增长；
- 关键数据能合法、稳定取得；
- 错误可以在发布、付款、删除或对外发送前被拦截；
- 结果能通过 rubric、样例集或业务指标复核。
如果任务低频、目标持续变化、没有验收口径，先做人工 SOP，不要先搭多 Agent。
1. 建立基线，不要直接写 Prompt
选择 10–30 个近期真实任务，记录人工基线：
| 指标 | 定义 |
|---|---|
| 任务成功率 | 首次交付通过验收的任务数 / 总任务数 |
| 一次通过率 | 无返工即通过的任务数 / 总任务数 |
| 周期 | 从收到完整输入到可交付输出的 elapsed time |
| 人工工时 | 研究、制作、复核、返工所花人时 |
| 单次成本 | 模型、工具、数据和人工复核成本之和 |
| 重试率 | 发生工具重试或整段重做的任务占比 |
| 严重错误率 | 错误发布、错误付款、数据泄露等高风险事件占比 |
没有这张基线表，就只能证明 Agent “能跑”，不能证明工作流变好了。
2. 从业务链路拆 Skill
先画业务链路，再按可验收结果拆 skill：
需求澄清 → 数据获取 → 证据整理 → 分析 → 产出 → 质检 → 人工批准 → 交付 → 反馈沉淀
每个 skill 至少包含：
name: competitor-evidence-pack
input_contract:
required: [product, market, competitors, time_window]
output_contract:
required: [claims, source_urls, captured_at, confidence, unknowns]
tools:
allow: [search, fetch]
deny: [publish, delete, payment]
acceptance:
- every material claim has a source
- source capture time is recorded
- unknown facts are labeled, not guessed
escalate_when:
- authenticated source is inaccessible
- sources conflict on a decision-critical fact
优先做单一职责 skill。只有当步骤间存在清晰依赖时，才增加 orchestrator。
3. Harness：让系统知道边界、记住纠错、持续评测
Prompt 只描述一次交互；harness 管理长期运行环境。至少包含五层：
- Context：品牌、客户、目标、禁区和数据权限；
- Skills：通用技能与客户专属技能分离，按任务选择调用；
- Memory：只沉淀经过确认的偏好、错误和纠正，不把猜测写成事实；
- Evaluation：固定样例集、rubric、回归测试和业务指标；
- Observability：每步输入摘要、工具调用、证据、成本、耗时、重试和最终批准人。
一次失败的正确处理方式不是无限加提示词，而是：记录失败类型 → 判断是数据、工具、推理还是验收问题 → 修改对应层 → 用旧样例集回归。
4. 选择编排方式
| 模式 | 适用情况 | 主要风险 |
|---|---|---|
| 顺序 | 后一步严格依赖前一步输出 | 上游错误级联 |
| 并行 | 多个独立来源或方案可同时产生 | 合并冲突、重复成本 |
| 路由 | 不同任务应调用不同专长 | 分类错误 |
| 主管—执行者 | 任务可拆成多个独立子任务 | 主管成为瓶颈 |
| 评审—修订 | 输出有明确 rubric，可迭代改进 | 无界循环、成本失控 |
默认从单 Agent + 多 skill 开始。只有观测数据证明吞吐或专长隔离确实需要并发，才升级为多 Agent。
5. 人工介入与权限
以下动作默认需要人工批准：
- 对外发布、群发、私信或代表个人表态；
- 付款、退款、采购和价格承诺；
- 删除、覆盖或批量修改数据；
- 使用未获授权的个人数据；
- 低置信度但会影响客户决策的结论。
What ships with it
5 files 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.
- 10d ago Changed · +14 lines 1ef245294835
- 1mo ago First seen · 181 lines · 83 tokens per session scan A c74c7953239b
agent-workflow-playbook is a skill published in the GitHub repository Gingiris-1031/gingiris-skills (87 stars, last pushed 10d ago), licensed MIT. It adds 83 tokens to every session and 2,341 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
takt
A workflow engine that runs a task through a sequence of steps defined in a YAML file, using separate coding agents for the work.
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).