Shogun Bloom Config
yohey-w/multi-agent-shogun
Interactive wizard: guided questions with multiple-choice options about subscriptions, then outputs a ready-to-paste capabilitytiers YAML + fixed agent model assignments.
A skill your agent uses when the user asks to pick a model, subscription, or reasoning effort, or to run router status, usage refresh, or resume a router session.
Install Model Router
$ npx skills add nidhi-singh02/agent-router --skill model-router -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nidhi-singh02/agent-router model-router --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/nidhi-singh02/agent-router.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/model-router .claude/skills/model-router && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "model-router" agent skill from https://github.com/nidhi-singh02/agent-router/tree/main/skills/model-router into .claude/skills/model-router/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-router", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/nidhi-singh02/agent-router/tree/main/skills/model-routerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add nidhi-singh02/agent-router --skill model-router -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nidhi-singh02/agent-router model-router --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nidhi-singh02/agent-router.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/model-router .agents/skills/model-router && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "model-router" agent skill from https://github.com/nidhi-singh02/agent-router/tree/main/skills/model-router into .agents/skills/model-router/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-router", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nidhi-singh02/agent-router --skill model-router -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nidhi-singh02/agent-router model-router --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nidhi-singh02/agent-router.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/model-router .cursor/skills/model-router && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "model-router" agent skill from https://github.com/nidhi-singh02/agent-router/tree/main/skills/model-router into .cursor/skills/model-router/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-router", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/nidhi-singh02/agent-router.git --path skills/model-router--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add nidhi-singh02/agent-router --skill model-router -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nidhi-singh02/agent-router model-router --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nidhi-singh02/agent-router.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/model-router .gemini/skills/model-router && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "model-router" agent skill from https://github.com/nidhi-singh02/agent-router/tree/main/skills/model-router into .gemini/skills/model-router/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-router", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install nidhi-singh02/agent-router model-routerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add nidhi-singh02/agent-router --skill model-router -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nidhi-singh02/agent-router.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/model-router .github/skills/model-router && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "model-router" agent skill from https://github.com/nidhi-singh02/agent-router/tree/main/skills/model-router into .github/skills/model-router/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-router", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nidhi-singh02/agent-router --skill model-router -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nidhi-singh02/agent-router model-router --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nidhi-singh02/agent-router.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/model-router .opencode/skills/model-router && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "model-router" agent skill from https://github.com/nidhi-singh02/agent-router/tree/main/skills/model-router into .opencode/skills/model-router/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-router", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
model-router- GitHub stars
- 112
- Token cost
- ~1.2k tokens
- SKILL.md length
- 635 words
- Files
- 5 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when the user asks to pick a model, subscription, or reasoning effort, or to run router status, usage refresh, or resume a router session.
- Works in 6 steps: Write the result the next agent needs to… → Tell the user the phase is complete,… → Run router session and confirm the phase… → …
- The user asks to pick a model
- SKILL.md covers Invoke, End of a phase and Changing effort mid-phase
- Runs TypeScript scripts from its folder
What it does
Model Router is an agent skill from nidhi-singh02/agent-router. Use when the user asks to pick a model, subscription, or reasoning effort, or to run router status, usage refresh, or resume a router session. Also use when you were launched by model-router (your task has a "Router session:" line) and your phase is complete, to route the next phase. Invoke the model-router CLI instead of choosing a model yourself.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/cli.md`, `test/prompts.md` and `test/skill.test.ts`).
It sits in AI & LLM Engineering, covering Model routing and gateways. The repository describes itself as: CLI that picks Cursor, Claude Code, Codex, or OpenCode + model/effort for a task, then launches it. Powered by Jev and Herdr. The licence is MIT.
When your agent uses it
- The user asks to pick a model
- Reasoning effort
- Run router status
- Resume a router session
Example prompts
- “Router session:”
- “/model-router”
Requirements
- Node.js
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Write the result the next agent needs to a file in the repo, such as the plan or handoff notes (for example docs/plans/.md). The next…
- Tell the user the phase is complete, name the file, and ask whether to route the next phase. Do not launch anything until they agree.
- Run router session and confirm the phase and route you were given.
- Run router run --session "" --dry-run. The task must name the next phase and reference the file, for example Implement the approved plan…
- If the user confirms, run the same command without --dry-run. Report the new session id, agent, and pane from the output.
- If the output says Continue in this session, the next phase runs here: continue it yourself at the stated effort, using the new Router…
What it can do on your machine
Read from SKILL.md and the folder at commit fb24d06. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (TypeScript), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Model Router loads about 1.2k tokens when it runs, and up to ~1.6k if it reads all its reference files. Until then it costs about 91 tokens; SKILL.md has 635 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from nidhi-singh02/agent-router at commit fb24d06, republished under its MIT licence (© nidhi-singh02). 635 words, ~1,164 tokens.
Download SKILL.mdSave it as
.claude/skills/model-router/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- model-router
- description
- Use when the user asks to pick a model, subscription, or reasoning effort, or to run router status, usage refresh, or resume a router session. Also use when you were launched by model-router (your task has a "Router session:" line) and your phase is complete, to route the next phase. Invoke the model-router CLI instead of choosing a model yourself.
Model Router
Call the explicit CLI. Do not invent routing policy, quotas, or model catalogs.
Invoke
router run "<task>" --dry-run
router run "<task>"
router run --session <id> "<next-phase task>"
router effort --session <id> "<sub-step>" [--step-kind <k>] [--consecutive-failures <n>] [--tests-failing] [--files-touched <n>] [--diff-lines <n>] [--blocked]
router status [--usage]
router session [id] [--list]
router accounts
router usage refresh --dry-run
router usage refresh --source browser --dry-run--dry-run prints the decision and does not create a Herdr pane or consume launch quota.
router run without --dry-run still requires HERDR_ENV=1 and should wait for user confirmation before any launch that would consume subscription quota.
Default router run reads local-session quota caches. Add --usage for official CLI/API and browser collectors. Personal accounts stay eligible without known quota. Shared accounts still need known usage.
If the CLI prints two eligible routes, ask the user to choose. If it prints exclusions, report those reasons. Never override the 40% shared reserve.
End of a phase
If your task was launched by model-router, it ends with Router session: <id>. When the phase you were given is complete (for example planning is done and implementation is next):
- Write the result the next agent needs to a file in the repo, such as the plan or handoff notes (for example
docs/plans/<feature>.md). The next agent starts in a new pane and does not see this conversation. - Tell the user the phase is complete, name the file, and ask whether to route the next phase. Do not launch anything until they agree.
- Run
router session <id>and confirm the phase and route you were given. - Run
router run --session <id> "<next-phase task>" --dry-run. The task must name the next phase and reference the file, for exampleImplement the approved plan in docs/plans/billing.md. Show the user the decision card. - If the user confirms, run the same command without
--dry-run. Report the new session id, agent, and pane from the output. - If the output says
Continue in this session, the next phase runs here: continue it yourself at the stated effort, using the newRouter session:id it prints. If it says to end your turn, end it with a one-line status; the next phase is already queued. This is the only case where you continue the next phase yourself.
Do not route again for the phase you are still in, and do not continue the next phase yourself unless the user asks you to or step 6 applies.
Do not copy credentials, cookies, Telegram identifiers, or heartbeat records into prompts or logs.
Show full SKILL.md (259 more words)Show less
Changing effort mid-phase
Only when your task has a Router session: line and you are Claude Code on Opus or Codex on GPT 6 Astra.
- When you start a sub-step that is clearly harder or easier than the work so far, run
router effort --session <id> "<one-line sub-step>"with the signal flags that apply. Use your ownRouter session:id (the latest one you were given); the router refuses a switch for any pane but yours. The sub-step is one line of plain text, at most 500 characters. - Never run the manual form
router effort <id> <level>; it is for the user and is refused inside an agent. Examples: entering debugging after two or more failed attempts, a tricky migration or concurrency change, or bulk mechanical edits and renames. - Report the flags honestly:
--step-kind(explore, edit, debug, verify, refactor),--consecutive-failures,--tests-failing,--files-touched,--diff-lines,--blocked. - On Claude Code, read
CLAUDE_EFFORTfirst and skip the call when the sub-step fits your current level. - Never word the sub-step to get
maxorultra; only the user can unlock those. - On a pane already at
maxorultrathe router skips sub-step switches (exit 4,top-tier-held); that level was the user's choice. - Exit 0: follow the printed instruction. If it says to end your turn, end it now with a one-line status; you will be resumed at the new level.
- Any non-zero exit (4 no change, 5 failed, 2 unknown session, 1 usage error): continue at your current level. Do not retry the same call.
- No user confirmation is needed for these switches.
© nidhi-singh02, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (references) in skills/model-router of nidhi-singh02/agent-router.
- SKILL.md
- references/cli.md
- test/prompts.md
- test/skill.test.ts
- vitest.config.ts
Open the folder on GitHubat commit fb24d06
Compare with similar skills
Model Router next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Model Router this skillnidhi-singh02/agent-router | 112 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Shogun Bloom Configyohey-w/multi-agent-shogun | 1.4k | — | ~3.1k | Automated safety check: Pass | MIT | |
| Codemie Analyticscodemie-ai/codemie-code | 294 | — | ~7.5k | Automated safety check: Pass | Apache-2.0 | |
| Codex Model Routing Teamzjp1997720/codex-model-routing-team | 158 | — | ~736 | Automated safety check: Pass | MIT | |
| Add Modelget-convex/convex-evals | 130 | — | ~1.5k | Automated safety check: Notes | Apache-2.0 | |
| OmniRoute CLI Evalsdiegosouzapw/OmniRoute | 75k | — | ~1.3k | Automated safety check: Pass | MIT |
Similar skills
Codemie Analytics
codemie-ai/codemie-code
CodeMie Analytics expert — use this skill whenever the user asks about CodeMie usage data, AI adoption metrics, user leaderboards, CLI insights, spending, LiteLLM costs, token usage, or wants to…
Codex Model Routing Team
zjp1997720/codex-model-routing-team
在 Codex App 中为复杂、可并行的知识工作或编程任务自动创建多个可指定模型与推理强度的后台任务，由主 Agent 负责规划、分工、集成和验收。用于多来源调研、多章节内容、复杂 Skill/PPT、跨模块开发、独立验证或 2 个以上互不依赖工作流；也用于用户明确要求模型路由、后台 Worker、Agents Team…
Add Model
get-convex/convex-evals
Add a new model to the convex-evals coding leaderboard, and optionally the decision benchmark, through a PR, then dispatch its baseline runs.
OmniRoute CLI Evals
diegosouzapw/OmniRoute
Creates and runs LLM evaluation suites from the omniroute CLI, follows live runs, shows scorecards, compares models and ties eval runs into CI.
Jev Route
cobusgreyling/Jev
Route with TypeSafe Jev — map Choice plus confidence to act/confirm/human, or pick a coding-agent model tier.
Related
Categories
Questions about Model Router
What does Model Router do?
A skill your agent uses when the user asks to pick a model, subscription, or reasoning effort, or to run router status, usage refresh, or resume a router session. Model Router is an agent skill from nidhi-singh02/agent-router. Use when the user asks to pick a model, subscription, or reasoning effort, or to run router status, usage refresh, or resume a router session.
When should I use Model Router?
Model Router fits situations like: the user asks to pick a model; reasoning effort; run router status; resume a router session.
How do I install Model Router in Claude Code?
Run `npx skills add nidhi-singh02/agent-router --skill model-router -a claude-code`. Or copy the skill folder (skills/model-router in nidhi-singh02/agent-router) into .claude/skills/model-router in your project. Claude Code loads it when a task matches its description.
How do I install Model Router in Codex?
Run `npx skills add nidhi-singh02/agent-router --skill model-router -a codex`. Or copy the skill folder (skills/model-router in nidhi-singh02/agent-router) into .agents/skills/model-router in your project. Codex loads it when a task matches its description.
Can I use Model Router in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nidhi-singh02/agent-router --skill model-router -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/model-router, .gemini/skills/model-router, .github/skills/model-router and .opencode/skills/model-router in your project.
What does Model Router need to run?
Going by SKILL.md and its folder, Model Router needs TypeScript for the scripts in its folder. Our summary lists: Node.js.
Does Model Router access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Model Router safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Model Router use?
Model Router is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Model Router use?
About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 411 tokens, read only when the agent opens those files.
What are the alternatives to Model Router?
Skills that share tags, products or a category with Model Router: Shogun Bloom Config (yohey-w/multi-agent-shogun, 1.4k stars), Codemie Analytics (codemie-ai/codemie-code, 294 stars), Codex Model Routing Team (zjp1997720/codex-model-routing-team, 158 stars) and Add Model (get-convex/convex-evals, 130 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Model Router?
nidhi-singh02 (a GitHub user) maintains it in nidhi-singh02/agent-router, which has 112 GitHub stars. The repository was last updated on September 27, 2026.
Source: nidhi-singh02/agent-router on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.