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-graph-searchnpx skills add synpulse8-opensource/pulse8-ai-cortex-knowledge-vault --skill cortex-graph-searchgit 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-graph-search)<a href="https://agentmods.dev/skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-graph-search"><img src="https://agentmods.dev/badge/skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-graph-search.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 5.1 | $0.00043 | $0.00493 |
| Opus 5 | $0.00022 | $0.00246 |
| Sonnet 5 | $0.00009 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
cortex-graph-search 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 5d 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 graph and search
Knowledge graph
- Storage:
cortex/graph/store.py— NetworkXDiGraph, persisted to{vault}/.cortex/graph.json. - Models:
cortex/vault/models.py—NodeType,EdgeType,GraphNode,GraphEdge. - Rebuild:
cortex/graph/builder.pyscans vault markdown and wikilinks.
Node types
note, tag, agent, session, daily, feedback (from path prefix or frontmatter type).
Edge types
links_to, authored_by, contradicts, derived_from, supersedes, memory_of, tagged_with.
API surface
- REST:
POST/GET/DELETE /api/v1/links,GET /api/v1/graph/stats - MCP:
vault_link,vault_context(expands neighbors from search hits)
QMD search
- Module:
cortex/search/qmd.py— wraps QMD CLI for keyword, semantic, and hybrid modes. - Debounce: After
vault_write,QmdDebounceschedules index refresh (cortex/search/debounce.py). - Modes:
keyword,semantic,hybrid(default hybrid in many call sites).
vault_context flow
- Run search with
query - Take top notes
- Expand graph neighbors up to
max_depth - Return combined context for agents
VaultWatcher sync
cortex/vault/watcher.py updates graph on file changes so disk edits stay consistent without full rebuild.
Debugging
- Empty search: check QMD index / vault path /
CORTEX_VAULT_PATH - Missing edges: run graph rebuild or trigger watcher; verify wikilink targets exist under allowed folders
- Stats:
GET /api/v1/graph/stats
Related skills
- Vault paths:
cortex-vault - MCP tools:
cortex-mcp
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.
- 5d ago First seen · 56 lines · 43 tokens per session scan A 1c0473755943
cortex-graph-search 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 43 tokens to every session and 493 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
rag-knowledge
Work with the RAG knowledge base — ingest documents, run semantic search, manage collections, or add a sync source/connector (Google Drive, S3). Use when populating or debugging the knowledge base, tuning retrieval, or adding a new document source. This project uses {{ cookiecutter.vectorstore }} + {{…
local-rag-core-maintainer
Maintain and verify the local-rag-core project. Use when working in this repository on code changes, documentation changes, MCP integration, pack lifecycle, backup or restore guidance, release readiness, GitHub publication, or operational verification.
research-add
Standard flow for adding a new research paper to MemRAG — upload, wait for wiki ingestion, verify output. Use when onboarding a new paper into the knowledge base.
docker-reset
Full Qdrant data reset — run when embedding dimension changes or data is corrupted. Destroys all vector data.
llm-wiki
The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources…
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.