agentmods.dev

cursorrules

Project instructions for choosing between ordinary text search and hypergrep, a code-search tool that can show functions, callers, and likely impact.

In plain words
What is it for?
Use them to inspect a codebase, find function definitions, trace callers and callees, check whether a library is used, and assess what a change may affect.
Why use it?
They help an agent search quickly for words while using deeper code analysis when it needs to understand how parts of the project connect.

Cursor rule for Cursor

19 5mo ago A scan 414 tokens original MIT
View the source file marjoballabani/hypergrep
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/marjoballabani/hypergrep/cursorrules
Clone the repo
git clone --depth 1 https://github.com/marjoballabani/hypergrep

Made for: Cursor.

Per session 414 This file is loaded in full into every session.
When invoked 414 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 $0.00414 $0.00414
Opus 5 $0.00207 $0.00207
Sonnet 5 $0.00083 $0.00083
Haiku 4.5 $0.00041 $0.00041

Measured 2d ago against content hash 602e1ef27231, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 2d 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.

agent-config/.cursorrules · 28 lines

What it actually says

This project has hypergrep installed globally. Use it instead of grep/ripgrep when you need structural understanding of code (function bodies, call graphs, impact analysis). For simple text searches, ripgrep is fine.

When to use hypergrep vs ripgrep:

  • Quick text search -> rg "pattern" . (faster for one-off)
  • Find + understand a function -> hypergrep -s "function" .
  • Search with token budget -> hypergrep --layer 1 --budget 800 --json "pattern" .
  • Who calls this / what breaks -> hypergrep --callers / --impact
  • Does project use X -> hypergrep --exists "redis" .
  • Codebase overview -> hypergrep --model "" .

Session start:

  • hypergrep --model "" . -- understand the codebase (run once)
  • hypergrep-daemon --background . -- optional, start if making 10+ searches (auto-stops after 30 min)

Commands:

  • hypergrep --layer 1 --budget 800 --json "pattern" . -- signatures + call graph in 800 tokens
  • hypergrep -s "pattern" . -- full function bodies (to edit)
  • hypergrep --callers "function_name" . -- who calls this?
  • hypergrep --callees "function_name" . -- what does this call?
  • hypergrep --impact "function_name" . -- what breaks? (run before editing)
  • hypergrep --exists "redis" . -- technology check (NO = guaranteed, YES = likely)

Rules:

  1. Run hypergrep --model "" . at session start
  2. Use hypergrep when you need to understand code, rg when you just need to find text
  3. Run hypergrep --impact before changing any function
  4. Use hypergrep -s instead of reading whole files for specific functions
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. 2d ago First seen · 28 lines · 414 tokens per session scan A 602e1ef27231

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository marjoballabani/hypergrep (19 stars, last pushed 5mo ago), licensed MIT. It adds 414 tokens to every session, about $0.0021 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 2026-08-30.

Researchai-agentsastcall-graphclaude-codeclicode-intelligence
Related

Other cursor rules, from other repositories

agents-first-convention

../../.agents/rules/agents-first-convention.md.

stainless-code/codemap · 11 tokens

architecture-priming

../../.agents/rules/architecture-priming.md.

stainless-code/codemap · 11 tokens

authoring-discipline

../../.agents/rules/authoring-discipline.md.

stainless-code/codemap · 11 tokens

plan-pr-inspiration-discipline

../../.agents/rules/plan-pr-inspiration-discipline.md.

stainless-code/codemap · 13 tokens

pr-comment-fact-check

../../.agents/rules/pr-comment-fact-check.md.

stainless-code/codemap · 11 tokens

verify-after-each-step

../../.agents/rules/verify-after-each-step.md.

stainless-code/codemap · 12 tokens