04-knowledge-vault

04-knowledge-vault is a cursor rule for Cursor from bybren-llc/safe-agentic-workflow. It costs 43 tokens per session (748 once invoked), scanned A, original, MIT.

A set of writing rules for maintaining a knowledge vault: a collection of linked notes that summarize trusted source documents. It defines the note format, linking rules, and how to record when information was checked.

In plain words
What is it for?
Use it when creating or updating knowledge-vault concepts, checking their metadata, maintaining links, or running the vault synchronization process.
Why use it?
It keeps notes consistent, traceable, and less likely to drift away from the code or documents they describe.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node knowledge-vault/scripts/validate-vault.mjs --vault <vault>.

Good fit Use it when creating or updating knowledge-vault concepts, checking their metadata, maintaining links, or running the vault synchronization process.

Compare 6 cursor rules from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow
agentmods
npx agentmods add rules/bybren-llc/safe-agentic-workflow/04-knowledge-vault

Made for: Cursor.

Wrote 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.

agentmods badge for 04-knowledge-vault

README.md
[![agentmods](https://agentmods.dev/badge/rules/bybren-llc/safe-agentic-workflow/04-knowledge-vault.svg)](https://agentmods.dev/rules/bybren-llc/safe-agentic-workflow/04-knowledge-vault)
Your own site
<a href="https://agentmods.dev/rules/bybren-llc/safe-agentic-workflow/04-knowledge-vault"><img src="https://agentmods.dev/badge/rules/bybren-llc/safe-agentic-workflow/04-knowledge-vault.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 748 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00748
Opus 5 $0.00022 $0.00374
Sonnet 5 $0.00009 $0.00150
Haiku 4.5 $0.00004 $0.00075

Measured 3d ago against content hash d252e67ca1fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

04-knowledge-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 3d 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.

.cursor/rules/04-knowledge-vault.mdc · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Vault Conventions

Activate this rule when writing or maintaining concepts in an OKF knowledge vault.

A vault is a map, not the territory. Source-of-truth docs stay where they live; code stays authoritative over everything, including the vault. A concept is a ~50-line map-card that summarizes and links — it never restates its source.

The Frontmatter Contract

Required on every concept: type, title, description (≤160 chars), tags, timestamp, status.

timestamp is the date the concept was last verified against its sources — not the date the file was edited. Optional: resource, domain, ticket, sources, docs, verified_against.

YAML subset only — scalars, double-quoted strings, inline lists, and two-space block lists. No nested maps, no multiline scalars. This is what keeps the validator dependency-free.

  1. Relative markdown links only. No wikilinks, no leading-slash paths, no repo-host URLs for files in this repo.
  2. Concept-to-concept links never leave the bundle.
  3. Links that leave the bundle appear only under ## Citations (index.md and guide types are exempt — they are navigation).
  4. Link only to concept IDs listed in _meta/manifest.json. If the concept does not exist, name it in prose and report it as a suggestion. Never invent a link.

Rule 4 is the one that matters most when several agents author in parallel. Without it you get a graph of plausible, confident, broken references.

Writing Rules

  • Summarize, never duplicate. If you are restating more than a paragraph, stop and link.
  • Code wins. Name the helper actually called, not the one the code should call. When code contradicts docs, document the code and note the discrepancy.
  • Section H2s must exactly match the type's template, in order. Do not add, remove, or rename.
  • Environment variable names may be mentioned; values never.
  • No emoji in concept files.

Drift Discipline

Staleness is computed, not felt: a concept is stale if and only if a path in its resource or sources changed since the manifest's baseline_sha.

Read the full file on GitHub · 71 lines

Changes

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.

  1. 3d ago First seen · 71 lines · 43 tokens per session scan A d252e67ca1fe

Subscribe to this mod's changes

04-knowledge-vault is a cursor rule published in the GitHub repository bybren-llc/safe-agentic-workflow (406 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 748 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 2026-09-03.