Borrowing it
Nothing to install: this file belongs to synpulse8-opensource/pulse8-ai-cortex-knowledge-vault. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/main/.cursor/skills/cortex-vault/SKILL.mdgit 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-vault)<a href="https://agentmods.dev/skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-vault"><img src="https://agentmods.dev/badge/skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-vault/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/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-vault"><img src="https://agentmods.dev/badge/skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-vault.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 | $0.00044 | $0.00703 |
| Opus 5.5 | $0.00018 | $0.00281 |
| Sonnet 5.5 | $0.00009 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
cortex-vault 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 2mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cortex vault
Code: cortex/vault/ (reader.py, writer.py, watcher.py, index.py, feedback.py, models.py).
Folder semantics
| Path | Purpose |
|---|---|
{VAULT_WIKI_DIR}/ |
Published Markdown articles (default wiki/; e.g. wiki1/) |
{VAULT_RAW_DIR}/ |
Source files before/during compilation (default raw/; e.g. raw1/) |
agents/ |
Agent definition notes |
sessions/ |
Per-session notes |
daily/ |
Daily notes |
feedback/ |
Feedback submissions (type: feedback) |
Paths in APIs are relative to vault root (e.g. wiki1/transformers.md when CORTEX_VAULT_WIKI_DIR=wiki1).
Configure via CORTEX_VAULT_RAW_DIR / CORTEX_VAULT_WIKI_DIR (or VAULT_RAW_DIR / VAULT_WIKI_DIR in .env for Compose).
.cortex/ metadata
| File | Purpose |
|---|---|
graph.json |
Serialized knowledge graph (NetworkX) |
index.md |
Human-readable vault index (rebuilt after bulk ops) |
log.md |
Append-only audit log (cortex/log/audit.py) |
ingest-manifest.json |
SHA-256 hashes of successfully compiled raw files |
ingest-skip-manifest.json |
Skipped/failed ingest records |
Notes and frontmatter
- Parsed via
python-frontmatterinread_note/write_note. infer_node_type()inreader.py: path prefix ortypein frontmatter →NodeType.- Common fields:
title,tags,authored_by,created_at,updated_at,source_path. - Feedback notes add
status: OPEN,related_paths(list of vault-relative.mdpaths).
Wikilinks and tags
- Wikilinks:
[[page]]or[[page|label]]— resolved underwiki/,agents/,sessions/,daily/,feedback/. - Tags in frontmatter become graph nodes
tag:{name}withtagged_withedges.
Validation rules
- Feedback
related_paths: each path must exist, be a file, and end in.md. Raw.txtcannot be linked — mention in feedback body instead. - Writes use
mode="create"or update;write_notesets timestamps and provenance.
VaultWatcher
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.
- 2mo ago First seen · 63 lines · 44 tokens per session scan A dd15feec2579
cortex-vault is a skill published in the GitHub repository synpulse8-opensource/pulse8-ai-cortex-knowledge-vault (15 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 703 once invoked, about $0.0002 per session on Opus 5.5. 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.
cortex-vault compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cortex-vaultsynpulse8-opensource/pulse8-ai-cortex-knowledge-vault | Skill | 15 | 3mo ago | Apache-2.0 | A | 44 | Cursor |
| session-ingestdnotitia/akb | Skill | 166 | yesterday | none | A | 74 | Claude Code |
| akb-ingestdnotitia/akb | Skill | 166 | yesterday | none | A | 87 | Claude Code |
| akb-querydnotitia/akb | Skill | 166 | yesterday | none | A | 50 | Claude Code |
| wiki-writeOshayr/LLM-Wiki | Skill | 50 | 6mo ago | MIT | A | 90 | Claude Code |
| llm-wiki-queryTrueHOOHA/LLM-Wiki | Skill | 22 | 3mo ago | Apache-2.0 | A | 66 | Claude Code, Codex |
| wiki-viewOshayr/LLM-Wiki | Skill | 50 | 6mo ago | MIT | A | 52 | Claude Code |