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/raymondchins/agentmap/cursor-rulegit clone --depth 1 https://github.com/raymondchins/agentmapWhat 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 | $0.00292 | $0.00292 |
| Opus 5 | $0.00146 | $0.00146 |
| Sonnet 5 | $0.00058 | $0.00058 |
| Haiku 4.5 | $0.00029 | $0.00029 |
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.
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:
- agentmap already oriented you and you need exact lines to edit
- The map is missing — run
agentmaponce to build.claude/agentmap/ - 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.
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.
- 2d ago First seen · 28 lines · 292 tokens per session scan A b3305a47be32
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.
Other cursor rules, from other repositories
coograph
Coograph project rules — workflow, code-graph, communication style.
agents-first-convention
../../.agents/rules/agents-first-convention.md.
architecture-priming
../../.agents/rules/architecture-priming.md.
authoring-discipline
../../.agents/rules/authoring-discipline.md.
plan-pr-inspiration-discipline
../../.agents/rules/plan-pr-inspiration-discipline.md.
pr-comment-fact-check
../../.agents/rules/pr-comment-fact-check.md.