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 michaelChe956/Cadence-skills --skill knowledge-base-bootstrapgit clone --depth 1 https://github.com/michaelChe956/Cadence-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/michaelche956/cadence-skills/knowledge-base-bootstrap)<a href="https://agentmods.dev/skills/michaelche956/cadence-skills/knowledge-base-bootstrap"><img src="https://agentmods.dev/badge/skills/michaelche956/cadence-skills/knowledge-base-bootstrap.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.04417 |
| Opus 5 | $0.00032 | $0.02209 |
| Sonnet 5 | $0.00013 | $0.00883 |
| Haiku 4.5 | $0.00006 | $0.00442 |
Grade A, and why
knowledge-base-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 8d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KnowledgeBase 初始化
概述
以目标项目的 cadence/knowledge-base/user-input/base-info.md 为唯一入口。先判定首次初始化、未完成初始化续跑、已完成保护或显式重新初始化,再校验六领域输入并按固定顺序编排领域 Skills。只生成和消费 Manifest Schema 4.0;输入不完整时返回模板和继续入口,不扩大扫描范围。
必读资源
- 执行前完整读取
references/input-contract.md。 - 缺失输入时引用
user-input/下的模板,不代替用户填写。 - 使用
assets/input-inventory-template.md生成输入解析清单。 - 使用
assets/manifest-template.yaml生成 Manifest。 - 需要核对典型判定时读取
references/demo.md。
固定输入
cadence/knowledge-base/user-input/
├── base-info.md
├── project-scope.md
├── data-model-scope.md
├── configuration-scope.md
├── middleware-scope.md
├── api-scope.md
├── page-scope.md
└── database-ddl.sql(可选)
用户输入和外部配置快照只读,不得覆盖、补写、复制或迁入知识库。
初始化状态不变量门禁
任何续跑、复用、领域调用、完成保护、显式重新初始化清理或 KnowledgeBase 写入前,都必须先只读校验 coverage.initialization。首次初始化尚无 Manifest 时,先在内存中构造符合本节约束的初始化块,六领域适用性确定后再写入;既有 Schema 4.0 Manifest 按以下规则处理:
- 整个
coverage.initialization块缺失是唯一兼容分支。不得依据登记或产物推断完成,必须先只读执行当前完整global-validation,再根据实际验收结果一次性回填完整初始化块;验收和回填前不得续跑、复用领域结果、调用领域 Skill、执行完成保护或修改其他产物。 - 初始化块存在时,必须同时满足以下全部不变量:
status只能是in_progress或complete;global_validation只能是pending、failed或passed。completed_stages是无重复字符串列表,元素只能是base-info、api、pages、overview、global-validation。列表必须保持固定顺序,是固定阶段序列在跳过不适用领域后的合法前缀或子序列;前置阶段尚未完成或合法跳过时,不得出现后续阶段,global-validation只能最后出现。skipped_stages是无重复对象列表,每项只能包含stage和reason两个键;stage只能是api或pages,reason必须为非空字符串。同一阶段不得重复,不得与completed_stages重叠;base-info、overview、global-validation永不可跳过。scope.api.status: 不适用时,api必须且只能出现在skipped_stages,不得出现在completed_stages;接口适用时不得跳过。pages按scope.pages.status使用同一规则。status: in_progress时,completed_at必须为空,global_validation只能是pending或failed,completed_stages不得包含global-validation;已完成和已跳过阶段仍须满足固定顺序。status: complete当且仅当:base-info、overview、global-validation已完成,适用的api、pages已完成,不适用的api、pages已正确跳过,global_validation: passed,completed_at非空,并且所有实际适用产物、索引、Manifest 登记、服务导航和证据满足对应阶段及global-validation完成条件。
- 初始化块存在但任一字段缺失、类型错误、值非法、重复、重叠、逆序、适用性不一致或完成状态与实际产物矛盾时,视为损坏状态。普通初始化、续跑、复用、领域调用、完成保护和 Update 必须立即停止且不修改任何产物;一次性报告每个异常字段的实际值、违反的不变量、受影响阶段和继续执行风险。不得把损坏状态当作续跑,不得自动补字段、重排、去重、改写状态。
- 可解析且
schema_version: "4.0"的 Manifest 存在损坏初始化块时,只有用户明确请求“重新初始化 Schema 4.0”才允许进入独立破坏性授权流程。先报告损坏字段实际值、无法信任现有初始化状态的影响,再列出拟清理的精确路径、人工内容丢失、Git/配置/变更历史基线失效风险和全量重建范围;必须取得用户针对上述精确范围与风险的再次明确授权。授权只允许继续执行清理前门禁,不能立即清理;此例外只绕过 initialization 不变量,不解释、不修复、不迁移损坏字段。Manifest 不可解析、缺少版本或版本不是 4.0 时仍禁止清理。 - 除第 4 项的破坏性重建例外外,每次阶段状态变化及任何原子写入前重新执行本门禁;只有当前状态合法且待写入的新状态也满足不变量时才可提交。
What ships with it
13 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.
- agents/openai.yaml 661 B
- assets/input-inventory-template.md 2.4 KB
- assets/manifest-template.yaml 2.2 KB
- references/demo.md 15 KB
- references/input-contract.md 15 KB
- user-input/api-scope.md 1.0 KB
- user-input/base-info.md 1.0 KB
- user-input/configuration-scope.md 2.4 KB
- user-input/data-model-scope.md 970 B
- user-input/database-ddl.sql 535 B
- user-input/middleware-scope.md 762 B
- user-input/page-scope.md 778 B
- user-input/project-scope.md 847 B
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.
- 8d ago First seen · 129 lines · 64 tokens per session scan A c0d6c7a34cba
knowledge-base-bootstrap is a skill published in the GitHub repository michaelChe956/Cadence-skills (11 stars, last pushed 6d ago), licensed MIT. It adds 64 tokens to every session and 4,417 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.