ai-knowledge-layer

A standing rule that points coding agents to the repository's `ai/` knowledge files before they explore or change code. It also defines how uncertain information and completed work must be labelled and recorded.

In plain words
What is it for?
Use it to locate modules and feature maps, check the history of earlier work, mark information as inferred or verified, and add each completed task to the work log.
Why use it?
It helps agents find the right parts of an unfamiliar repository and keeps project knowledge traceable instead of leaving undocumented assumptions.

Cursor rule for Cursor

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/kunalsuri/ai-fication-kit/ai-knowledge-layer
Clone the repo
git clone --depth 1 https://github.com/kunalsuri/ai-fication-kit

Made for: Cursor.

Per session 270 This file is loaded in full into every session.
When invoked 270 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 $0.00270 $0.00270
Opus 5 $0.00135 $0.00135
Sonnet 5 $0.00054 $0.00054
Haiku 4.5 $0.00027 $0.00027

Measured 3d ago against content hash ec93676467c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-knowledge-layer 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/ai-knowledge-layer.mdc · 23 lines

What it actually says

This repo has an AI knowledge layer under ai/. Read ai/INDEX.md first — it is the role → path manifest for finding the right map for your task — then ai/guide/MODULE_MAP.md to locate code by directory before you crawl the tree.

Provenance. Anything written into ai/ is [inferred] until a human flips it to [verified]. Never flip that tag yourself.

Record work. Every unit of work ends with a row appended to ai/lab/WORKLOG.md — even work done outside these rules. Backtick every artifact path in the row: verify checks backtick-quoted path claims against the tree (plain-text links are not validated).

See AGENTS.md (already read by Cursor) for the full rule set. The other rules in this directory (.cursor/rules/*.mdc) mirror the kit's skills for Claude Code and prompt files for GitHub Copilot — invoke them the same way you would any other Cursor rule.

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 · 23 lines · 270 tokens per session scan A ec93676467c0

Subscribe to this mod's changes

ai-knowledge-layer is a cursor rule published in the GitHub repository kunalsuri/ai-fication-kit (3 stars, last pushed 4d ago), licensed Apache-2.0. It adds 270 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.