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 skills add V-Songbird/slag --skill routergit clone --depth 1 https://github.com/V-Songbird/slagWrote 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/skills/v-songbird/slag/router)<a href="https://agentmods.dev/skills/v-songbird/slag/router"><img src="https://agentmods.dev/badge/skills/v-songbird/slag/router/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/skills/v-songbird/slag/router"><img src="https://agentmods.dev/badge/skills/v-songbird/slag/router.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 | $0.00131 | $0.01428 |
| Opus 5 | $0.00066 | $0.00714 |
| Sonnet 5 | $0.00026 | $0.00286 |
| Haiku 4.5 | $0.00013 | $0.00143 |
Grade A, and why
router 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 9d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jetbrains-routing
When this applies
A mcp__<ide>__* tool (webstorm, rider, idea, pycharm, phpstorm, goland, rubymine, clion, rustrover, …) is listed in the session's available tools. Check once per session — if none is present, the JetBrains MCP server isn't connected and this guidance doesn't apply (use native tools; the hook fails open).
Why route
- Live diagnostics:
get_file_problems/lint_filesreturn the IDE's in-memory inspection results — notsc/gradle/mypycold start. - Unsaved-buffer reads:
read_filereflects the editor's current buffer, including changes the user hasn't saved. - Project-index search:
search_text/search_regex/search_symbol/search_fileskipnode_modules, build outputs, and.gitignore'd paths via the project model, and return 1-based line/column coordinates.
Prefix
JetBrains auto-configure registers the MCP server under the lowercase product name (webstorm, rider, idea, pycharm, …) — that becomes the mcp__<prefix>__* tool prefix. The hook auto-detects the running IDE. If you renamed your mcpServers entry, or run several IDEs at once, JETBRAINS_MCP_PREFIX=<name> picks the target.
Tool mapping
Use the JetBrains replacement whenever a mcp__<ide>__* tool is registered. The PreToolUse hook denies a native call with a reason naming the IDE tool and the pre-translated project-relative path — going native first costs the round-trip for nothing.
Full mapping with required parameters and usage notes: references/tool-map.md. Load it before the first routed call in a session. The high-traffic ones:
| Native | IDE tool | Required params |
|---|---|---|
| Read | read_file |
file_path (relative or absolute; mode/start_line/max_lines for partial reads) |
| Grep | search_regex / search_text |
q — optionally paths=["src/**"] to scope |
| Glob | search_file |
q (glob, project-relative) |
| Edit | replace_text_in_file |
pathInProject, oldText, newText — pass replaceAll explicitly (IDE default is true) |
| Write (new file) | create_new_file |
pathInProject, text |
| Bash build / tsc | build_project — or get_file_problems(filePath=…) for one file |
|
| Bash test | execute_run_configuration after get_run_configurations |
configurationName |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 77 lines · 131 tokens per session scan A feb3f03a475f
router is a skill published in the GitHub repository V-Songbird/slag (1 stars, last pushed 4d ago), licensed MIT. It adds 131 tokens to every session and 1,428 once invoked, about $0.0007 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…