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/QuickerHub/quicker-rpcWrote 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/quickerhub/quicker-rpc/qkrpc)<a href="https://agentmods.dev/rules/quickerhub/quicker-rpc/qkrpc"><img src="https://agentmods.dev/badge/rules/quickerhub/quicker-rpc/qkrpc/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/quickerhub/quicker-rpc/qkrpc"><img src="https://agentmods.dev/badge/rules/quickerhub/quicker-rpc/qkrpc.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 | $0.00048 | $0.01098 |
| Opus 5.5 | $0.00019 | $0.00439 |
| Sonnet 5.5 | $0.00010 | $0.00220 |
| Haiku 4.5 | $0.00005 | $0.00110 |
Grade A, and why
qkrpc 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 2mo 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qkrpc agent rules
Canonical file — copied to workspace .cursor/rules/ via scripts/Sync-QkrpcAgentRules.ps1 and to Cursor plugin via qkrpc agent setup --cursor-plugin.
Scope gate
Apply this rule only when:
- the user is editing Quicker actions / subprograms, or
- files under the qkrpc disk root (
.quicker/), or - you are calling
qkrpc_*MCP /qkrpcCLI for authoring
Do not treat QuickerOrg/Quicker (or other product repos) as QKRPC_WORKSPACE_ROOT. Disk edits belong in the configured workspace (usually quicker-workspace). Prefer project .cursor/mcp.json over a user-global Cursor plugin.
Before editing
docsaction=get topicoverview, thenauthoring-workflow- Subprograms:
subprogram-workflow - Disk layout:
docstopicworkspace-editingor MCP resourcequicker://workspace/readme
Task routing
| Goal | MCP (preferred) | CLI (--json) |
|---|---|---|
| Local edit action / global subprogram | qkrpc_action_get / qkrpc_subprogram_get → edit .quicker/ → workspace_program action=patch |
action get / subprogram get → edit → apply |
| Remote publish action (动作库) | — | action publish / action update (--changelog on update) |
| Remote publish subprogram (子程序库) | — | subprogram publish / subprogram update (--changelog on update) |
| Run / debug with step output | qkrpc_action mode=debug |
action run --trace |
On trace failure read failureLocation, stackTrace, logExcerpt (auto tail from quicker.log). See tools/qkrpc/docs/agent-action-debug-workflow.md.
| Step inputs schema | qkrpc_step_runner_search → qkrpc_step_runner_get | step-runner search → step-runner get |
| Icons (WPF / WebView) | qkrpc_fa | fa search / fa resolve |
| Connectivity | qkrpc_health → on failure qkrpc_wait | health / wait |
Never action publish / action update for subprograms (wrong API). Never guess inputs without step-runner get.
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.
- 2mo ago First seen · 68 lines · 48 tokens per session scan A baac2487709f
qkrpc is a cursor rule published in the GitHub repository QuickerHub/quicker-rpc (14 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 1,098 once invoked, about $0.0002 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 2026-08-30.
Other cursor rules, from other repositories
hatch3r-dotnet-patterns
.NET 10 + C# 14 conventions covering minimal APIs, nullable reference types, async/await, Entity Framework Core, dependency injection, structured logging, and xUnit testing.
pre-flight-check
Mandatory fail-fast quality gate — run Typecheck, Lint, Test, and Security Audit sequentially before declaring any task done or committing code.
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.
graphql
GraphQL: schema design, resolvers, performance.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.