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/sachinshelke/toolsconnector/cursorrulesgit clone --depth 1 https://github.com/sachinshelke/ToolsConnectorWhat 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 | $0.00214 | $0.00214 |
| Opus 5 | $0.00107 | $0.00107 |
| Sonnet 5 | $0.00043 | $0.00043 |
| Haiku 4.5 | $0.00021 | $0.00021 |
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.
What it actually says
Cursor/Windsurf Guidelines for ToolsConnector
Always follow these rules when developing in this workspace:
- Use Python 3.9+ conventions.
- Every class and function MUST have full type hints. No typing
Anyunless absolutely unavoidable. - Use Pydantic models for request/response serialization.
- Auto-generate docstrings using Google Style. Ensure
Args:,Returns:, andRaises:clauses are always populated. - In connectors, always utilize the
@actiondecorator mapped intoolsconnector.core.action. - Keep lines under 100 characters.
- Focus on single-responsibility. If a connector file gets larger than 500 lines, extract the types and helpers into
types.pyandhelpers.py. - Never commit credentials, even test ones. Assume all code is fully open source.
- Verify import boundaries: files in
connectors/cannot import fromserve/.core/cannot import fromconnectors/orserve/.
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 · 14 lines · 214 tokens per session scan A abf4111a0122
cursorrules is a cursor rule published in the GitHub repository sachinshelke/ToolsConnector (5 stars, last pushed 9d ago), licensed Apache-2.0. It adds 214 tokens to every session, about $0.0011 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
git-workflow
Cursor rule "git-workflow" from comet-ml/opik, covering git workflow, branch naming, commit format, pr title and jira key references (commit messages & pr body).
agents
Cursor rule "agents" from comet-ml/opik, covering agent deployment, domain routing, frontend structure, task approach and execution.
code-style
Cursor rule "code-style" from comet-ml/opik, covering code style, comments, don't over-engineer and stay focused.
security
Cursor rule "security" from comet-ml/opik, covering security, never and always.
ehs-ims-conventions
EHS IMS app — RBAC, data layer, tRPC, migrations, AI boundaries.
project-overview
Project overview and conventions for the Idun Agent Platform monorepo.