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/freepeak/leankg/leankg-rulegit clone --depth 1 https://github.com/FreePeak/LeanKGWrote 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/freepeak/leankg/leankg-rule)<a href="https://agentmods.dev/rules/freepeak/leankg/leankg-rule"><img src="https://agentmods.dev/badge/rules/freepeak/leankg/leankg-rule.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 5.1 | $0.00000 | $0.00424 |
| Opus 5 | $0.00000 | $0.00212 |
| Sonnet 5 | $0.00000 | $0.00085 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
leankg-rule 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- leankg-rule — 100% identical, 0 lines differ
What it actually says
LeanKG Mandatory Rule
MANDATORY 4-Tier Search Fallback Chain
Tier 1: LeanKG MCP (mcp_status → search_code / find_function / query_file)
Tier 2: leankg CLI (leankg query "X" --kind name)
Tier 3: rtk (rtk grep "X" --path .)
Tier 4: grep/rg (LAST RESORT)
LeanKG MCP Tools
mcp_status- Check readiness firstsearch_code("X")- Find by name/typefind_function("X")- Function definitionsquery_file("*X*")- Files by nameget_impact_radius(file)- Change impactget_context(file)- Read contentget_dependencies(file)- Importsget_dependents(file)- Reverse depsget_callers("func")- Who callsget_call_graph("func")- Full graph
ABSOLUTE BANS
- NEVER skip to grep when LeanKG available
- NEVER use Glob before LeanKG for code
- ONLY exception: non-code files (config, docs)
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.
- 6d ago First seen · 46 lines · 0 tokens per session scan A d31023352212
leankg-rule is a cursor rule published in the GitHub repository FreePeak/LeanKG (216 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 424 tokens. 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 2026-08-30.
Other cursor rules, from other repositories
cursor-rules
Live code graph for this repo — what changes together, who owns what, why two things are linked, 360° context on any symbol, durable notes.
04-spatial-parser
Guidelines for Spatial RAG and Markdown parsing.
02-python-standards
Python coding standards, libraries, and concurrency safety.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
codebase
Forensic codebase brief for AI agents.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.