ivn-knowledge

Project-specific guidance automatically synchronized from ivn, a tool for storing and applying project knowledge. It records design decisions, coding patterns, pitfalls, dependencies, and pending work.

In plain words
What is it for?
Use it as working rules for fixture-tested exports, adapter registries, preserved Markdown content, stable specifications, and deterministic output.
Why use it?
It gives coding agents the project context they need to follow existing decisions and avoid known mistakes.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/boona13/ivn/ivn-knowledge
Clone the repo
git clone --depth 1 https://github.com/boona13/ivn
Per session 264 This file is loaded in full into every session.
When invoked 264 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00264 $0.00264
Opus 5 $0.00132 $0.00132
Sonnet 5 $0.00053 $0.00053
Haiku 4.5 $0.00026 $0.00026

Measured yesterday against content hash ef0840e647cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ivn-knowledge 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 yesterday.

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.

test/fixtures/compatibility/golden/ivn-knowledge.mdc · 50 lines

What it actually says

Project Knowledge (via ivn)

Auto-generated by ivn sync-rules. Do not edit manually.

Project Context

  • The compatibility suite keeps adapters honest.

Architectural Decisions

These decisions have been made. Follow them consistently:

  • We decided every exported rule file should be fixture-tested.

Coding Patterns & Conventions

Always follow these established patterns:

  • We use adapter registries instead of monolithic sync files.

Known Gotchas & Pitfalls

Be aware of these issues. Warn the developer if relevant:

  • ⚠ Watch out: managed markdown blocks must preserve user-written content.

Dependencies & Constraints

  • This depends on stable spec versions and deterministic markdown output.

Active Work & TODOs

  • Add more fixture projects for future adapters.

Capture New Knowledge

When you discover something important while working — a decision, gotcha, bug fix, or pattern — persist it so future sessions already know:

ivn remember "what you learned and WHY" --type gotcha --tags relevant,tags

Types: decision · pattern · gotcha · debug · dependency · todo

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. yesterday First seen · 50 lines · 264 tokens per session scan A ef0840e647cf

Subscribe to this mod's changes

ivn-knowledge is a cursor rule published in the GitHub repository boona13/ivn (2 stars, last pushed 2mo ago), licensed MIT. It adds 264 tokens to every session, about $0.0013 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 2026-08-31.