ai-kb

ai-kb is a cursor rule for Cursor from iamironz/ai-config-bundle. It costs 277 tokens per session, scanned A, original, MIT.

A set of shared rules and reference material for an AI coding assistant, including a searchable knowledge base, commands, and project guidance.

In plain words
What is it for?
Use it to discover relevant coding rules, load their supporting documents, and provide the rule context before handling a task.
Why use it?
It tells the assistant which project rules to find and read before starting work. This helps keep its changes consistent with the team's existing practices.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

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/iamironz/ai-config-bundle/ai-kb
Clone the repo
git clone --depth 1 https://github.com/iamironz/ai-config-bundle

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 ai-kb

README.md
[![agentmods](https://agentmods.dev/badge/rules/iamironz/ai-config-bundle/ai-kb.svg)](https://agentmods.dev/rules/iamironz/ai-config-bundle/ai-kb)
Your own site
<a href="https://agentmods.dev/rules/iamironz/ai-config-bundle/ai-kb"><img src="https://agentmods.dev/badge/rules/iamironz/ai-config-bundle/ai-kb.svg" alt="Measured on agentmods" height="20"></a>
Per session 277 This file is loaded in full into every session.
When invoked 277 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 5.1 $0.00277 $0.00277
Opus 5 $0.00138 $0.00138
Sonnet 5 $0.00055 $0.00055
Haiku 4.5 $0.00028 $0.00028

Measured 6d ago against content hash 8904637b6273, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ai-kb 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 6d 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/ai-kb.mdc · 28 lines

What it actually says

This rule is Cursor's KB / RAG entrypoint.

Canonical KB Entry Points

  • How to use the KB (operational loop + ck retrieval): ai-kb/AGENTS.md
  • Rule discovery and loading: ai-kb/rules/INDEX.md
  • Command catalog: ai-kb/commands/INDEX.md

RAG-First Requirements (Mandatory)

  • Before starting any task: read the three entry points above.
  • Follow the operational loop in ai-kb/AGENTS.md:
    • discover relevant rules via ck search (MCP server ck) first
    • use ai-kb/rules/INDEX.md only as a fallback when ck is unavailable
    • load the relevant Level 1 rules + Level 2 subdocs before acting
  • Output a <rule_context> block quoting the rules you will follow, then proceed.

Cursor Integration (Wiring)

  • Slash command wrappers: .cursor/commands/* (delegate to ai-kb/commands/*)
  • Optional post-turn analyzer hook: .cursor/hooks/kb-post-turn-analyzer.py (via .cursor/hooks.json)
  • KB recommendation queue: .cursor/kb-recommendations/*.md (review then apply)
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. 6d ago First seen · 28 lines · 277 tokens per session scan A 8904637b6273

Subscribe to this mod's changes

ai-kb is a cursor rule published in the GitHub repository iamironz/ai-config-bundle (2 stars, last pushed 5mo ago), licensed MIT. It adds 277 tokens to every session, about $0.0014 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.

Related

Other cursor rules, from other repositories

nauro-adopt

Seeds Nauro's project store from an existing repo. Use after nauro adopt has run locally. On filesystem-capable surfaces, reads docs (README, manifests, ADRs, Memory-Bank) for rationale and inspects code, config, tests, lockfiles, and recent git history for evidence, then surfaces targeted probes that turn evidence…

Nauro-AI/nauro · 89 tokens

nauro-context

Writes durable shared context into Nauro's project store so other agents (a later session or a parallel one) can discover and pull it, finds and reads context another agent left, or captures a resumable brief so your own next session in this environment picks up cleanly. Three modes. Author writes a shared brief for…

Nauro-AI/nauro · 272 tokens

honcho_rules

Honcho persistent memory — capture every conversation, recall past context, and build a growing model of the user. Activates on every conversation.

matthewdcage/llm-swarm-router · 1,412 tokens

memory-bank

You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…

leshchenko1979/fast-mcp-telegram · 1,623 tokens

pytest-integration-tests

Below is an example test. Notice the following.

iloveitaly/llm-ide-rules · 0 tokens

python-app

Here's how the python application is organized.

iloveitaly/llm-ide-rules · 1,524 tokens