Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add hxt9805/cadence/plugin install cadenceWrote 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/hxt9805/cadence/cadence-init)<a href="https://agentmods.dev/skills/hxt9805/cadence/cadence-init"><img src="https://agentmods.dev/badge/skills/hxt9805/cadence/cadence-init/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/hxt9805/cadence/cadence-init"><img src="https://agentmods.dev/badge/skills/hxt9805/cadence/cadence-init.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 | $0.00089 | $0.01796 |
| Opus 5 | $0.00044 | $0.00898 |
| Sonnet 5 | $0.00018 | $0.00359 |
| Haiku 4.5 | $0.00009 | $0.00180 |
Grade A, and why
cadence-init 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cadence Init
初始化 cadence 工作流。双模式:新项目 / 已有项目。
1. 检查现有状态
读取项目根,检查 cadence/:
_INDEX.md+_ACTIVE.md都在(已初始化 v0.2.2+)→ 询问要重做项目快照吗?[r/n]。r跳到 § 3.3 已有项目模式 [A];n退出(无需 /clear,bootstrap 在本 session 启动时已注入)。_INDEX.md在 +_ACTIVE.md不在(v0.2.x 旧格式)→ § 2 迁移- 都不在 → § 3 init
- 其他异常(如
_INDEX.md不在但_ACTIVE.md在)→ 提示用户手动修复或删cadence/后重跑
2. v0.2.x 旧版本迁移(inline)
主 session 直接处理(不再调 subagent)。
检测到旧版 cadence 目录(v0.2.x 前)。v0.2.2 将 _INDEX.md 拆为
"纯索引 _INDEX.md + 纯活跃 _ACTIVE.md"。迁移前建议先 commit。继续?[Y/N]
N → abort。Y → 执行:
- 读
cadence/_INDEX.md。 - 按映射拆 section:
- 「当前活跃决策」/「待决清单」/「TODO」/「最近讨论」→
_ACTIVE.md - 「项目简述」/「话题词典」/「快速导航」→ 留
_INDEX.md - 未识别 section → 留
_INDEX.md末尾(加<!-- cadence 未识别 -->注释)
- 「当前活跃决策」/「待决清单」/「TODO」/「最近讨论」→
_ACTIVE.md若超 8 条活跃决策上限,inline 三档:⚠️ 检测到 N 条活跃决策,新上限 8 条。 (a) Claude 推荐归档清单(按日期倒序最老 N-8 条) (b) 我自己选要归档哪些 (c) 保留全部(暂时超限,下次记决策时会提示整理)- 更新话题词典 pointer:
→ 活跃决策改为→ _ACTIVE.md#活跃决策或@active。 - 展示 diff 摘要 → 用户确认 →
Edit _INDEX.md+Write _ACTIVE.md(IO 失败回滚,不留半迁移状态)。 - 完成告知:
📝 已迁移:_INDEX.md(NN→MM 行 / 纯索引)+ _ACTIVE.md(新建 KK 行)。详见 git diff cadence/
→ § 4 汇报产物(无需 /clear,bootstrap 在本 session 启动时已注入)。
3. init 主流程
3.1 判断项目状态
- 空目录,或只有版本控制/编辑器元数据与空 README → 新项目模式(§ 3.2)
- 有任何有意义的项目材料 → 已有项目模式(§ 3.3)。项目材料包括但不限于:
- 源代码、配置和构建清单;
- 研究材料、数据说明、实验记录和参考文献;
- 文稿、提纲、素材和风格指南;
- 学习记录、课程计划、练习与评估;
- 运营计划、日历、预算、流程和复盘;
- 其他能体现项目目标、主产物、约束或进度的文件。
不要因为项目没有 src/、package.json 或 Git 就判为新项目。忽略缓存、依赖、
构建输出和系统临时文件后,只要仍有实质材料就是已有项目。
3.2 新项目模式
创建目录骨架:
cadence/
├── _INDEX.md ← scaffolds/_INDEX.md
├── _ACTIVE.md ← scaffolds/_ACTIVE.md
├── _archive/.gitkeep
└── discussions/.gitkeep
极简 onboarding(允许 [TBD]):
项目档案(初版):
- 项目是什么:???
- 给谁用:???
- 已知硬约束:???
告诉我能说的部分,其他留白也 OK。
用户提供的字段写入 _INDEX.md 的「项目简述」;不提供的保持 [TBD]。用户说「随便聊聊」→ 跳过 onboarding。
3.3 已有项目模式
[A] 快速扫描生成「项目快照」(推荐)
[B] 先不扫描,按需了解
- [A]:创建目录骨架(同 § 3.2)→ 调
project-scannersubagent。扫描器先做 通用发现,再按已观察到的材料选择领域适配器;软件适配器只是其中一种:
完成后展示 scanner 的请按 ${CLAUDE_PLUGIN_ROOT}/skills/cadence-init/agents/project-scanner.md 的规范扫描本项目。 项目路径:{project_root} 输出:cadence/discussions/00-project-snapshot.md + 01-inconsistencies.mdsuggested_index_fields(每字段标[来源: X],[推断]优先级低需额外确认)。让用户选[Y]全部回填 /e<编号>编辑某项 /[N]全保持 [TBD]。 - [B]:只创建目录骨架,不调 subagent。
What ships with it
4 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.
- 9d ago First seen · 137 lines · 89 tokens per session scan A eb969518f440
cadence-init is a skill published in the GitHub repository hxt9805/cadence (5 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,796 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 skills, from other repositories
flow-next-plan
Plan a feature into a flow-next spec with tasks in .flow/. Use when asked to plan, spec out, or break down work (fn-N ids).
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
flow-next
Manage .flow/ tasks and specs. Use for show or list tasks, task status, what is ready, show fn-N. NOT for planning or executing (use the plan and work skills).
kanban
Use when a prompt contains a new bug/feature/change not yet tracked, or when an item's status changes — capture and maintain it in the project's beads tracker (Inbox→Backlog with Definition of Ready, priorities, the pipe-separated note format).
subtask-update
Update subtask with fixes or new steps. Two trigger modes: (A) Auto-called by autoworker:gate-check on FAIL — reads FAIL info, adds supplementary steps. (B) User calls with a finding/bug during testing — diagnoses, fixes, updates subtask. Both modes end by invoking autoworker:dispatch to re-enter the loop.
checkpoint
Record progress to subtask: Phase completion (from autoworker:code) or test results (from autoworker:test). Auto-detects upstream type from conversation context. Ends by calling autoworker:dispatch.