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.
git clone --depth 1 https://github.com/Ozzeron/prompt-packWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/ozzeron/prompt-pack/cursor-bridge)<a href="https://agentmods.dev/rules/ozzeron/prompt-pack/cursor-bridge"><img src="https://agentmods.dev/badge/rules/ozzeron/prompt-pack/cursor-bridge/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/ozzeron/prompt-pack/cursor-bridge"><img src="https://agentmods.dev/badge/rules/ozzeron/prompt-pack/cursor-bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01095 | $0.01095 |
| Opus 5.5 | $0.00438 | $0.00438 |
| Sonnet 5.5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
cursor-bridge 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt-pack routing bridge
For any non-trivial coding request, do not answer immediately. First decide
whether one of the prompt-pack rules in .cursor/rules/ applies, and invoke
it explicitly with @<rule-name> before responding.
Mandatory routes (do not answer ad-hoc when these match):
- Whole-project review or audit — the user asks to look at, review,
audit, or assess the codebase as a whole, and does not point you at
a diff, PR, or specific changes. This includes "проревьюй весь
проект", "перевір весь репо", "check the whole repo", "audit
the project", "general code quality review". You must invoke
@repo-auditbefore producing the report. Answering ad-hoc here is the failure mode this rule exists to prevent. - PR / diff review — the user pointed at a diff, PR, branch range, or
named changeset. You must invoke
@code-reviewbefore producing findings. - Security review of changes or a module — you must invoke
@security-review.
For every other intent in the table below, prefer explicit @<rule-name>
invocation when the request is high-stakes (refactor planning, schema
design, RLS work). Cursor's auto-loading of agent-requested rules is
best-effort; explicit invocation is the only guarantee.
Common mappings
| User intent (any language) | Use rule |
|---|---|
| PR / diff review ("review this PR", "проверь diff", "перевір PR") | @code-review |
| Whole-project review or audit ("проревьюй весь проект", "загальний аудит", "check the whole repo") | @repo-audit |
| Security review of changes or a module ("security review", "перевір безпеку") | @security-review |
| Frontend audit of an existing UI codebase ("audit the frontend", "проаудитуй фронт") | @frontend-audit |
| Database review (schema/query/migration) | @database-review |
| Find code duplication / DRY audit | @duplication-audit |
| Debug a failing test or bug | @debugger |
| Build a frontend feature / page ("add a feature", "сделай страницу", "зроби фічу") | @frontend-feature |
| Build a backend endpoint / API ("add an endpoint", "добавь API") | @backend-api |
| Design a new UI / screen | @ui-designer |
| Design new tables / data model | @database-schema |
| Write a DB migration | @database-migrations |
| Supabase RLS / auth / migration workflow | @postgres-supabase |
| Plan a refactor / migration | @refactor-planner |
| Write tests for existing code | @test-writer |
| Write or update docs (README, ADR, AGENTS.md, etc.) | @doc-writer |
Write or modify Dockerfile / docker-compose / containerize / .dockerignore ("write a Dockerfile", "containerize", "докеризуй", "напиши Dockerfile") |
@docker |
| Wrap up / hand off completed work | @handoff |
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.
- 1mo ago First seen · 81 lines · 1,095 tokens per session scan A 8a0659a33138
cursor-bridge is a cursor rule published in the GitHub repository Ozzeron/prompt-pack (8 stars, last pushed 1mo ago), licensed MIT. It adds 1,095 tokens to every session, about $0.0044 per session on Opus 5.5. 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
reqforge-dev-build
Dev Builder — implementation execution. Build code phase by phase following DEV-PLAN, each Task goes through review → fix loop.
cursor-tools-mastery
Cursor 3.7 runtime guide: choose the right tool, canvases, Design Mode, /worktree, /best-of-n, Await, and parallel execution where safe.
fable5-reasoning
Fable 5 reasoning protocols: task interpretation, risk-first decomposition, approach selection, interleaved thinking, hypothesis ledgers, premortems, calibration, and the stuck-strategy ladder. Load for complex, ambiguous, or long-horizon tasks, for debugging strategy, or whenever progress stalls.
cursor-agent-orchestration
Cursor 3.7 orchestration guide: when to plan, when to delegate, nested subagents, multi-environment handoffs, /best-of-n, and Await for long-running branches.
cursor-mcp-optimization
Cursor 3.7 MCP optimization: browser Design Mode, canvases, Figma, Cloudflare tools, MCP Apps structured content, and direct action patterns.
minimax-mcp-tools
MCP and web-tool guidance: current-doc retrieval, direct-tool preference, MCP Apps structured content, and version-aware external lookups.