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.
npx agentmods add rules/kunalsuri/ai-fication-kit/check-driftgit clone --depth 1 https://github.com/kunalsuri/ai-fication-kitWrote 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/rules/kunalsuri/ai-fication-kit/check-drift)<a href="https://agentmods.dev/rules/kunalsuri/ai-fication-kit/check-drift"><img src="https://agentmods.dev/badge/rules/kunalsuri/ai-fication-kit/check-drift.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.00220 |
| Opus 5 | $0.00009 | $0.00110 |
| Sonnet 5 | $0.00004 | $0.00044 |
| Haiku 4.5 | $0.00002 | $0.00022 |
Grade A, and why
check-drift 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 4d 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.
What it actually says
Run the mechanical verification and drift analysis to inspect the state of the ai/ knowledge-base:
- Run the path verifier:
node install.mjs verify . --strict - Run the drift detector with git history comparison:
node install.mjs drift . --git --strict - Run
git statusto inspect modified and untracked files.
If any issues are reported, or if git status reveals newly added or modified source files/templates that are not yet covered in the maps:
- Draft updates to
ai/guide/MODULE_MAP.mdorai/guide/FEATURE_MAP.mdto map new folders, files, or features, or to update stale verified dates. - Mark any changes you draft as
[inferred]. - Report findings to the user and outline what needs their manual review.
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.
- 4d ago First seen · 19 lines · 18 tokens per session scan A 49a6442ca01c
check-drift is a cursor rule published in the GitHub repository kunalsuri/ai-fication-kit (3 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 220 once invoked, about $0.0001 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.
Other cursor rules, from other repositories
x-harness
Use only light, standard, deep. Do not use small, medium, large.
01-qa-agent
QA AGENT PERSONA: Principles, Anti-patterns, workflows.
cursorrules
ALWAYS start your session by reading AGENTS.md and .memory/wiki/hot.md to get project context before suggesting code or answering questions.
head-of-product
Head of Product persona — planning, user stories, UX decisions, scope guardian. Use when discussing product strategy, PRDs, user research, feature proposals, or backlog prioritization.
bash-style
Bash 核心规范：禁止行尾注释、文件写入用 tee、Heredoc 默认禁止变量展开.
chinese-language
CRITICAL: You MUST respond in Simplified Chinese at ALL times unless explicitly requested otherwise. 回复、注释、commit message 使用简体中文。技术术语保持英文原文。.