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/snyk/agentic-integration-wrappers/cursorrulesgit clone --depth 1 https://github.com/snyk/agentic-integration-wrappersWhat 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 | $0.00702 | $0.00702 |
| Opus 5 | $0.00351 | $0.00351 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
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
** general **
- always be concise, direct and don't try to appease me.
- DOUBLE CHECK THAT YOUR CHANGES ARE REALLY NEEDED. ALWAYS STICK TO THE GIVEN GOAL, NOT MORE.
- I repeat: don't optimize, don't refactor if not needed.
- Adhere to the rules, fix linting & test issues that are newly introduced.
- the
issueIDis usually specified in the current branch in the formatIDE-XXXX. - always create an implementation plan and save it to the directory under ${issueID}_implementation_plan but never commit it. take it as a reference for each step and how to proceed. Get confirmation that the plan is ok.
- Maintain existing code patterns and conventions
** how to implement **
- don't comment what is done, instead comment why something is done if the code is not clear
- always write and update test cases. iterate until they pass.
- please check the makefile - make lint runs the linter, other targets might be relevant as well.
- use existing mocks, don't write new ones.
- if you use mocks, use gomock to generate them.
- always run the tests after editing.
- always use the linter
- don't change code that does not need to be changed. only do the minimum changes.
- this is not a library. if files are not used or needed anymore, delete them instead of deprecating them.
- if a tool call fails, analyze why it failed and correct your approach. don't prompt the user for help.
- if you don't know something, read the code instead of assuming it.
- commenting out code to fix errors is not a solution. instead, fix the error.
** security **
- determine the absolute path of the project directory. you can do that e.g. by executing pwd on the shell within the directory.
- always use snyk for sca and code scanning. scan with both tools. you need to pass the absolute path of the directory we are scanning.
- run snyk code tests after each edit. pass the absolute path of the project directory as a parameter
- run snyk sca tests after updating go.mod and pass the absolute path of the project directory as a parameter.
- run snyk sca and code test before committing. if not test data, fix issues before committing.
** fixing issues **
- fix security issues if they are fixable. take the snyk scan results and the test results as input
- don't fix test data
** committing **
- when asked to commit, always use conventional commit messages (Conventional Commit Style (Subject + Body)). be descriptive in the body. if you find a JIRA issue (IDE-XXXX) in the branch name, use it as a postfix to the subject line in the format [IDE-XXXX]
- consider all commits in the current branch when committing, to have the context of the current changes. when asked to push, always use 'git push --set-upstream origin $(git_current_branch)' with git_current_branch being the current branch we are on
- never force push
- never push without asking
- never commit the hashicorp gomod
- regularly fetch main branch and offer to merge it into git_current_branch
- after pushing offer to create a PR on github. analyze the changes by comparing the current branch ($(git_current_branch)) with origin/main, and craft a PR description and title. use the github pr template in this repository
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 · 45 lines · 702 tokens per session scan A e1834053db23
cursorrules is a cursor rule published in the GitHub repository snyk/agentic-integration-wrappers (11 stars, last pushed 26d ago), licensed Apache-2.0. It adds 702 tokens to every session, about $0.0035 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
cursor-asdd
ASDD contribution rules for this repository.
selectools-providers
Rules for working with LLM provider adapters in selectools.
05-daemons-ipc
Use this rule to understand the roles of the HAPPE/IDA/mcp-hostd daemons, how HAPPE and IDA communicate via IPC, find the IPC message structure definitions, trace the memory retrieval flow, and identify daemon responsibilities.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.