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 zxc663/shisan-xinuo-workflow --skill shisan-xinuo-flowsgit clone --depth 1 https://github.com/zxc663/shisan-xinuo-workflowWrote 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/zxc663/shisan-xinuo-workflow/shisan-xinuo-flows)<a href="https://agentmods.dev/skills/zxc663/shisan-xinuo-workflow/shisan-xinuo-flows"><img src="https://agentmods.dev/badge/skills/zxc663/shisan-xinuo-workflow/shisan-xinuo-flows/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/zxc663/shisan-xinuo-workflow/shisan-xinuo-flows"><img src="https://agentmods.dev/badge/skills/zxc663/shisan-xinuo-workflow/shisan-xinuo-flows.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 | $0.00191 | $0.01099 |
| Opus 5.5 | $0.00076 | $0.00440 |
| Sonnet 5.5 | $0.00038 | $0.00220 |
| Haiku 4.5 | $0.00019 | $0.00110 |
Grade A, and why
shisan-xinuo-flows 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
流程包（shisan-xinuo-flows）
家族结构：本包=流程细节层（「教做什么」）；纪律与跑道（判级/门禁/红线/复述/GATE）在核心
shisan-xinuo-workflow。依赖声明：本包假设核心在场——本包不含纪律条款，遇纪律问题以核心与注入核心为准（独立可装，但建议同装）。
加载后行动契约（本包被加载时先做三件事）
- 触发确认：一行说明为什么加载本包（命中了哪类流程/模板需要）。
- 首动作：读
references/workflows.md的对应分节（按任务类型定位，见索引）；任务现状模糊先走 §0.0 澄清流程。 - 出口产物：按对应工作流的分步产物交付（每步有出口产物，无产物不进下一步）；模板从
templates/复制后填写，不原地编辑。
索引
references/workflows.md 分节：§0.0 澄清流程（状态澄清四步）｜§0.1 前置与总纲｜§0.2 联网调研可信依据（权威性四级：一手源>实证源>社区口碑>榜单热度）｜§0.3 产品完善度诊断｜§0.4 双调研规划（工程师+产品双视角）｜§0.5-0.6 调研矩阵与分流决策表｜§1 新功能/新项目开发 15 步｜§2 Bug 修复与问题排查 7 步｜§3-§9 其余任务类工作流｜§10 会话诊断与复盘（七维外部分析+path:line 举证）｜§11 教训生命周期与上下文卫生（域/态状态机+污染清洗，教训账=核心包 references/lessons.md）｜复用决策链（五问）｜质量门禁细节。
templates/ 七件：plan-template.md（规划）｜acceptance-criteria-template.md（验收标准）｜task-record-template.md（任务记录含 GATE 字段）｜retrospective-template.md（复盘）｜rollback-point-template.md（回滚点）｜prompt-budget.template.md（提示词预算）｜compact-retention-template.md（压缩保留指令）。
与核心对接
- 核心路由表命中后加载本包：调试/排错→§2；新功能/多文件→§1；设计类→§0.4+设计规范留档（
docs/design-specs/）；任务类型不明→§0.5-0.6 对照表。 - 纪律面（判级/必问/门禁/GATE/跳过声明）不在本包——由核心与注入核心常驻承担；本包产物进入核心的「出口产物/门禁」检查点。
- 与
shisan-xinuo-roles（角色包）协作：审查/验收环节可由核心 dispatch 到角色包。
边界
不预载非当前任务所需的分节；不复制纪律条款（单一源=核心）；模板为起手骨架，填入后即项目产物（史料不进模板正文）。
What ships with it
8 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.
- references/workflows.md 34 KB
- templates/acceptance-criteria-template.md 975 B
- templates/compact-retention-template.md 748 B
- templates/plan-template.md 1.8 KB
- templates/prompt-budget.template.md 1.3 KB
- templates/retrospective-template.md 873 B
- templates/rollback-point-template.md 891 B
- templates/task-record-template.md 1.9 KB
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 Changed f32bc397322e
- 4d ago Changed fdc8152cb7ef
- 6d ago Changed · -29 tokens per session d401df637641
- 9d ago Changed 604463aad9d5
- 16d ago Changed 374cf3d9d91c
- 23d ago Changed 0192899c95bd
- 25d ago Changed 63b1514c3973
- 26d ago Changed a23e20e2ecd6
- 28d ago First seen · 41 lines · 220 tokens per session scan A 14030004c514
shisan-xinuo-flows is a skill published in the GitHub repository zxc663/shisan-xinuo-workflow (38 stars, last pushed 3d ago), licensed MIT. It adds 191 tokens to every session and 1,099 once invoked, about $0.0008 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 2026-09-18.
Other skills, from other repositories
triage-issue-reports
Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.
pod-init
Initialize CocoPlus project bundle in the current directory. Creates .cocoplus/ directory structure, copies all templates, initializes AGENTS.md, project.md, flow.json, and creates the initial git commit. Run this once per project before using any other CocoPlus command.
cocoharvest
Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…
cococonverge
CocoPivot — multi-pod convergence synthesizer. Deterministically deduplicates findings from N parallel pod outputs into one prioritized, coordinated action plan. Invoked via $pivot run/show/status/clear.
plan
Enter the Plan phase of CocoBrew. Runs CocoSpec quality gate pre-flight, reads spec.md and discuss.md (if present), invokes Coco native plan mode as a mandatory gate, captures the approved plan to plan.md, creates initial flow.json template, and commits. Must have $spec completed first.
lean-debt
CocoLean shortcut debt ledger — harvests cocoplus: comment markers across the CocoPod and produces a ranked deferral report sorted by ceiling imminence and age.