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-bootstrap)<a href="https://agentmods.dev/skills/hxt9805/cadence/cadence-bootstrap"><img src="https://agentmods.dev/badge/skills/hxt9805/cadence/cadence-bootstrap/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-bootstrap"><img src="https://agentmods.dev/badge/skills/hxt9805/cadence/cadence-bootstrap.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 | $0.00117 | $0.02953 |
| Opus 5 | $0.00059 | $0.01477 |
| Sonnet 5 | $0.00023 | $0.00591 |
| Haiku 4.5 | $0.00012 | $0.00295 |
Grade A, and why
cadence-bootstrap 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cadence 工作流
本项目使用 cadence 工作流管理讨论和决策档案。本文是 L0 协议精炼摘要;细则单一权威源在 ${CLAUDE_PLUGIN_ROOT}/skills/project-discuss/references/。冲突时以 L2 为准。
§ 1. ASSUME INTERRUPTION
context 随时可能被 /compact 或重置。新 session / /compact 后必须重做 § 10「session 启动行为」,不假设"上次读过的还在"。
§ 2. 目录约定
- 讨论产物在
cadence/(不在docs/)。docs/保留给项目原有用途。 - 事项真实状态以
cadence/_ACTIVE.md为准(活跃决策、待决、TODO、最近讨论)。
§ 3. 项目档案落点
- 决策结论 →
_ACTIVE.md活跃决策(一行摘要 + pointer) - 待决问题 →
_ACTIVE.md待决清单 - TODO →
_ACTIVE.mdTODO - 完整 reasoning / trade-off →
discussions/<date>-<slug>.md(整 阶段产物) - 流式 entry →
streaming/<YYYY-MM-DD>-<topic-slug>.md(记 阶段,append-only)
§ 4. 三段式记录判定
承接决定是否记录
持久语义增量决定是否新建 entry
影响等级决定记录多详细
- 承接:用户明确或隐含确认了结论或中间决定;未承接的探索不记成 accepted。
- 持久语义增量:只有目标、范围、规则、顺序、边界、状态、风险、依赖、否决项或后续行动发生稳定变化时才新建 entry。重复确认不重复记。
- 影响等级:按可逆性、影响范围、损失风险、持续时间、外部承诺、不确定性和协作复杂度选择记录深度,不按项目领域套固定模板。
强信号(视为已承接):
- 接受性表态(「嗯」「好」「OK」「可以」)
- 用户基于此推进后续讨论("那下一步 Y 怎么办" → 说明 X 已是既定前提)
- 用户在新决策中引用已讨论的 X
弱信号(不算承接):
- 沉默 / 反问质疑("确定吗?"还在讨论)
不确定是否形成持久增量时,优先写一条 Light entry;不要假设重要内容以后一定会再次出现,也不要把整理负担转交给用户。
| profile | 适用 | 最低保真度 |
|---|---|---|
| Light | 局部、低风险、易撤回 | context + chosen |
| Standard | 影响一个阶段、多个产物或后续讨论 | Light + rationale + 真实存在的替代/依赖/待决 |
| High | 难逆、长周期、外部承诺或高损失风险 | context + chosen + rationale + 适用的通用语义槽 |
完整规则、通用语义槽、跨领域示例和敏感信息边界见 L2 ../project-discuss/references/recording-fidelity.md;格式和流程见 recording-protocol.md。
§ 5. 记录动作(happy path)
命中判据 → append entry 到 cadence/streaming/<YYYY-MM-DD>-<topic-slug>.md → 告知一行 📝 已记:<摘要> → streaming/...(不索取确认)。
§ 5a. Recommended entry format (YAML frontmatter + markdown body)
---
id: e1
created: 2026-05-21T12:30:00+08:00
status: accepted
detail_profile: standard
chosen: 显式「开始学习」按钮触发
context: 教学模式 UX 设计访谈中讨论"首次进入"入口形态;担心自动触发误启动 session
rationale: 保留用户主动控制,同时避免额外确认弹窗
options:
- 显式按钮触发
- 自动进入教学
- 弹窗询问
rejected:
- 自动进入: 用户路过页面就启动 session,缺乏控制感
- 弹窗询问: 多一步骤打断流程
---
## E1: 教学入口用「开始学习」按钮触发
用户点击 → 创建 session + AI 发开场白
后续进入:自动恢复 active session,不重发开场白
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 · 180 lines · 117 tokens per session scan A a69b404de658
cadence-bootstrap is a skill published in the GitHub repository hxt9805/cadence (5 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 2,953 once invoked, about $0.0006 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.