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-contextgit 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-context)<a href="https://agentmods.dev/skills/michaelche956/cadence-skills/knowledge-base-context"><img src="https://agentmods.dev/badge/skills/michaelche956/cadence-skills/knowledge-base-context.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 | $0.00123 | $0.04028 |
| Opus 5 | $0.00062 | $0.02014 |
| Sonnet 5 | $0.00025 | $0.00806 |
| Haiku 4.5 | $0.00012 | $0.00403 |
Grade A, and why
knowledge-base-context 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KnowledgeBase 任务上下文
概述
从用户当前任务出发,沿知识库语义、当前代码、数据模型、配置四条独立证据路径渐进读取,生成支持下游工作的最小任务上下文包。本 Skill 只接受 Manifest 4.0,是需求、Design、Plan、Coding、Testing、Review 或 Debug 的前置上下文阶段,不代替下游工作。
上下文准备完成后,调用方必须继续用户原始任务;只有用户明确只要求加载、整理或保存上下文时,才在上下文包处结束。
手动入口
- Claude Code 插件:
/cadence-init:knowledge-base-context - Codex:
$knowledge-base-context
自动触发只由 Frontmatter description 决定。Manifest 在触发后提供 Schema、授权范围和证据基线,不参与 Skill 发现。
必读资源
- 执行渐进读取前读取
references/progressive-retrieval-guide.md。 - 识别主辅画像后读取
references/task-profiles.md中对应画像。 - 需要核对完整输出形状时读取
references/demo.md。 - 只有用户明确要求保存任务上下文时,使用
assets/task-context-template.md。
强制边界
- 四条路径同等重要,必须分别记录来源、缺口和停止原因,不得把数据模型或配置并入“当前代码”。
- 每次任务都检查与逻辑表、数据源、配置组和配置键的直接关系。确认无直接关系后记录结论并停止该方向,不扫描全部数据模型或配置包。
- 只在 Manifest 4.0 的工程、数据模型和配置授权范围内读取;不得重新解释用户输入或自行扩大范围。
- 外部配置快照目录全程只读;不连接配置中心、数据库、中间件或远程环境,不执行部署、发布、启动或迁移脚本。
- 默认只把上下文返回当前会话,不创建任务文件。
- 不修改业务代码、KnowledgeBase、Manifest、变更包或下游交付物。
- 不复制完整源码、整篇知识库文档或配置快照,只保留摘要、稳定 ID、精确位置和必要短片段。
- 工作区未提交修改属于当前代码证据,不清理、不覆盖、不恢复。
- 敏感配置只返回配置键、用途、状态和绑定位置;值统一写为
<redacted>。 - 四条证据路径逐层执行:每层必须输出本层证据摘要(来源、精确位置、本层结论、停止原因)后才允许进入下一层;四条路径各自必须有证据或停止原因,禁止留白方向。
- 默认只扩展一跳;画像必需字段仍缺关键证据时才扩第二跳,扩跳必须记录触发理由。
工作流程
0. Schema 4.0 前置校验
- 读取当前项目适用的
AGENTS.md、CLAUDE.md和项目规则。 - 定位
cadence/knowledge-base/manifest.yaml,只接受schema_version: "4.0"。 - 必读以下 Manifest 4.0 信息:
scope.projects、scope.data_models、scope.configurations。evidence.data_model_sources中的 DDL、迁移、Entity、Mapper、SQL 和人工资料状态。evidence.configuration_snapshots.baseline的快照标识、环境、外部目录、授权指纹、scope_summary、纳入文件数量或清单摘要、服务摘要、文件规则摘要和来源元数据。update.last_change_package与update.processed_packages。git.repositories中的分支、baseline_commit和仓库范围。
- 获取当前分支、提交和工作区状态,只用于识别任务相关基线漂移。
Manifest 缺失、Schema 不是 4.0 或缺少任务所需授权范围时立即停止,报告缺失路径或版本,并引导执行 knowledge-base-bootstrap。不得兼容其他 Schema、自动迁移或回退为普通全仓分析。
1. 识别任务画像与种子
固定画像只有七类:需求澄清、Design、Plan、Coding、Testing、Review、Debug。选择一个主画像,可附加最多两个辅助画像。
从用户请求提取业务词,以及已知页面、API、服务、逻辑表、字段、数据源、配置组、配置键、文件、符号、错误信息、目标环境、MR 和变更包。用户明确点名对象优先于模糊业务词。
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.
- 8d ago First seen · 235 lines · 123 tokens per session scan A fa281326dee3
knowledge-base-context is a skill published in the GitHub repository michaelChe956/Cadence-skills (11 stars, last pushed 6d ago), licensed MIT. It adds 123 tokens to every session and 4,028 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 2026-08-30.
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.