cursor-rule

Project instructions for using agentmap, a searchable map of TypeScript and JavaScript code relationships. They tell an agent when to use the map and when to read or search files directly.

In plain words
What is it for?
They help locate symbols, identify importers and dependents, check reuse, estimate change impact, orient within a repository, and fall back to direct searches when needed.
Why use it?
They provide a consistent way to answer structural code questions such as who imports a file or what a change may affect. They also avoid using the map for raw text or unsupported files.

Cursor rule

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/raymondchins/agentmap/cursor-rule
Clone the repo
git clone --depth 1 https://github.com/raymondchins/agentmap
Per session 292 This file is loaded in full into every session.
When invoked 292 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 $0.00292 $0.00292
Opus 5 $0.00146 $0.00146
Sonnet 5 $0.00058 $0.00058
Haiku 4.5 $0.00029 $0.00029

Measured 2d ago against content hash b3305a47be32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-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 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.

skills/cursor-rule.mdc · 28 lines

What it actually says

This project can use agentmap (@raymondchins/agentmap) — a queryable import/symbol map at .claude/agentmap/.

Before Grep/Glob for structural questions (where is a symbol, who imports a file, reuse check, blast radius), prefer:

agentmap --any <query>          # file → symbol → feature → git-grep fallback
agentmap --find <Symbol>        # exported symbols matching name
agentmap --relates <file.ts>    # imports, dependents, related files
agentmap --map --tokens 400     # cheap repo orientation

Use Read/Grep directly when:

  1. agentmap already oriented you and you need exact lines to edit
  2. The map is missing — run agentmap once to build .claude/agentmap/
  3. Searching raw strings, logs, or non-TS files

Cursor MCP (optional): agentmap --mcp exposes the same queries as tools.

Note: --features only detects Next.js app/ routes; TanStack src/routes/ repos often show features (0).

Package: @raymondchins/agentmap — not the unrelated PyPI/npm agentmap package.

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 · 292 tokens per session scan A b3305a47be32

Subscribe to this mod's changes

cursor-rule is a cursor rule published in the GitHub repository raymondchins/agentmap (46 stars, last pushed 3d ago), licensed MIT. It adds 292 tokens to every session, about $0.0015 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.