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 agentmods add skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-compilernpx skills add synpulse8-opensource/pulse8-ai-cortex-knowledge-vault --skill cortex-compilergit clone --depth 1 https://github.com/synpulse8-opensource/pulse8-ai-cortex-knowledge-vaultWrote 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/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-compiler)<a href="https://agentmods.dev/skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-compiler"><img src="https://agentmods.dev/badge/skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-compiler.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.00555 |
| Opus 5 | $0.00019 | $0.00278 |
| Sonnet 5 | $0.00008 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
cortex-compiler 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 4d 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
Cortex compiler
Pipeline overview
raw/ → Compiler (LLM) → wiki/*.md → graph + QMD index
Key modules
| Module | Role |
|---|---|
cortex/compiler/compiler.py |
Single-file compile |
cortex/compiler/bulk.py |
Recursive directory scan, concurrency, manifests |
cortex/compiler/prompts.py |
LLM prompts |
cortex/mcp/tools.py |
vault_ingest, vault_compile |
Manifests (under .cortex/)
ingest-manifest.json— SHA-256 of successfully compiled raw files (skip on re-run unlessforce)ingest-skip-manifest.json— failures and skips
REST endpoints
| Endpoint | Behavior |
|---|---|
POST /api/v1/ingest |
JSON content → raw/ |
POST /api/v1/ingest/upload |
Multipart upload |
POST /api/v1/compile |
Async compile all pending (202) |
GET /api/v1/compile/status |
Job status |
POST /api/v1/bulk-ingest |
Scan source_dir on server filesystem |
Bulk ingest body
{
"source_dir": "/ingest",
"concurrency": 4,
"force": false,
"dry_run": false
}
Logs (cortex.compiler.bulk): Scanning source directory, per-file progress. Also logged from cortex.api.routes on request receipt.
Recursive scan: source_dir is walked recursively; subfolder structure is preserved under the vault raw dir (e.g. source_dir/abcde/a.html → {VAULT_RAW_DIR}/abcde/a.html).
Common failure: source_dir not mounted in container → 400 before bulk runs.
MCP
vault_ingest— write bytes toraw/vault_compile— trigger compile pass
Config
LLM provider settings in cortex/config.py (model, API keys via env). See .env.example.
Related skills
- Vault layout:
cortex-vault - Deploy
/ingestmount:cortex-deploy - API details:
cortex-api
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.
- 4d ago First seen · 71 lines · 39 tokens per session scan A 6b79030ede72
cortex-compiler is a skill published in the GitHub repository synpulse8-opensource/pulse8-ai-cortex-knowledge-vault (14 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 555 once invoked, about $0.0002 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
llm-wiki-ingest
Ingest a newly provided raw source into the LLM Wiki OKF bundle. Use whenever the operator asks to add a source to the wiki, process a file under raw/sources or raw/assets, summarize and file an article/paper/transcript, or mentions ingestion, importing sources, or updating the wiki from a document.
tdoc_orchestrator
"文档创作与美化的统一编排入口（本地通道）。当用户意图涉及文档写作或排版美化时调用。职责：识别意图 → 编排 stage 能力链（S1 创作 / S2 美化 / S3 HTML→DOCX 转换）→ 委派 generateword/generateword/generateword 执行；S3 产出 .docx 后强制 系统下载卡片（自动生成） 打开预览，本 skill 调用结束。⚠️ 文档编辑不在本 skill 内承接，由 tencent-docs-routing skill 处理。不适用：纯代码文件、非文档类操作。".
doc_typeset
| 消费 design tokens + 文档内容，输出排版美化的 HTML。 内置 7 种垂类模板（合同/学术论文/公文/商务报告/会议纪要/研报/年报）和 4 个装饰组件，所有样式通过 CSS 变量引用 Token，禁止裸值。 在 generateword 流水线中每当需要将文本内容转化为结构化美化 HTML 时，必须使用此 skill； 不要自己写 HTML 或内联 CSS——doc-typeset 是内容→HTML 的唯一标准转换路径。.
html_to_docx
| 将 HTML 字符串或文件高保真转换为 Microsoft Word (.docx) 文档。 支持 CSS 变量预处理、10+ 种 HTML 元素精确映射、14 种 CSS 属性映射、中文字体、4 种装饰组件、TOC 目录、页眉页脚、图片嵌入。 提供 CLI（subprocess）和 Python API 双模式调用；在需要将 HTML 文档转为可编辑 Word 文件时使用此 skill。.
format_extract
> 把 .docx 文档转为语义化 HTML + 提取内嵌图片（标题层级、表格样式、段落缩进、字体颜色等结构信息），供调用方做后续格式分析；也可独立评估 HTML 转换质量。适用场景（技术性底层调用）："docx 转 HTML"、"提取 docx 结构为 HTML"、"HTML 转换质量评估"。本 Skill 是底层格式提取工具，不自行判断是否应被触发、不猜测输出位置——是否调用、何时调用、产物落在哪一律由上层调用方（如 generateword）决定，调用时必须显式传入 --output-dir。用户关于"文档排版 / 套模板 / 参考这份 docx 生成"等需求，应由 orchestrator 统一编排入口接管，不要旁路直点本…
library
当要写/整理在线文档、建数据表增删改查、导入 CSV·Excel、做看板/dashboard/运营页/汇报页、md 转网页或演示 HTML 发布、建目录、上传下载网盘文件、审阅修订、分享协作，以及提到资料库/知识库/网盘/空间/workbuddy.cn/space 链接时使用。资料库是 WorkBuddy 原生的内容管理、分享协作与轻发布模块，覆盖在线文档（doc）、网页链接（link）、结构化数据表（database）、数据/汇报页面（page）、网盘文件（drive）与空间管理（manage）；凡说资料库/知识库或出现 space 链接、未显式点名腾讯文档/飞书/Notion/乐享/金山文档/iWiki 等外部产品时一律走本…