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.
Capability-aware model routing for Codex, Copilot, Claude and provider APIs.
Install Model Routing Patterns
$ npx skills add softspark/ai-toolkit --skill model-routing-patterns -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install softspark/ai-toolkit model-routing-patterns --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/softspark/ai-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/app/skills/model-routing-patterns .claude/skills/model-routing-patterns && 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-routing-patterns" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/model-routing-patterns into .claude/skills/model-routing-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-routing-patterns", 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/softspark/ai-toolkit/tree/main/app/skills/model-routing-patternsType 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 softspark/ai-toolkit --skill model-routing-patterns -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install softspark/ai-toolkit model-routing-patterns --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/app/skills/model-routing-patterns .agents/skills/model-routing-patterns && 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-routing-patterns" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/model-routing-patterns into .agents/skills/model-routing-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-routing-patterns", 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 softspark/ai-toolkit --skill model-routing-patterns -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install softspark/ai-toolkit model-routing-patterns --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/app/skills/model-routing-patterns .cursor/skills/model-routing-patterns && 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-routing-patterns" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/model-routing-patterns into .cursor/skills/model-routing-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-routing-patterns", 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/softspark/ai-toolkit.git --path app/skills/model-routing-patterns--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 softspark/ai-toolkit --skill model-routing-patterns -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install softspark/ai-toolkit model-routing-patterns --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/app/skills/model-routing-patterns .gemini/skills/model-routing-patterns && 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-routing-patterns" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/model-routing-patterns into .gemini/skills/model-routing-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-routing-patterns", 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 softspark/ai-toolkit model-routing-patternsInstalls 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 softspark/ai-toolkit --skill model-routing-patterns -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .github/skills && cp -r skills-src/app/skills/model-routing-patterns .github/skills/model-routing-patterns && 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-routing-patterns" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/model-routing-patterns into .github/skills/model-routing-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-routing-patterns", 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 softspark/ai-toolkit --skill model-routing-patterns -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install softspark/ai-toolkit model-routing-patterns --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/app/skills/model-routing-patterns .opencode/skills/model-routing-patterns && 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-routing-patterns" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/model-routing-patterns into .opencode/skills/model-routing-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-routing-patterns", 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-routing-patterns- GitHub stars
- 179
- Token cost
- ~2.4k tokens
- SKILL.md length
- 1,190 words
- Files
- 1
- Skills in repo
- 112
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Capability-aware model routing for Codex, Copilot, Claude and provider APIs.
- Tasks that involve Model routing and gateways
- SKILL.md covers Claude Code: available…, Reviewed model reference…, Effort and caching and Pattern 1: explicit task routing, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Model Routing Patterns is an agent skill from softspark/ai-toolkit. Capability-aware model routing for Codex, Copilot, Claude and provider APIs. Triggers: model routing, model selection, reasoning effort, approved fallback, cost, escalation.
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Model routing and gateways. The repository describes itself as: Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI… The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Model routing and gateways
Example prompts
- “/model-routing-patterns”
Requirements
- Python 3
- Pre-approved tools (allowed-tools): Read
What it can do on your machine
Read from SKILL.md and the folder at commit d64db2b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
Read
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
platform.claude.comlearn.chatgpt.comdevelopers.openai.com
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 Routing Patterns loads about 2.4k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 1,190 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 softspark/ai-toolkit at commit d64db2b, republished under its Apache-2.0 licence (© softspark). 1,190 words, ~2,439 tokens.
Download SKILL.mdSave it as
.claude/skills/model-routing-patterns/SKILL.md (or your agent's skills folder).- name
- model-routing-patterns
- description
- Capability-aware model routing for Codex, Copilot, Claude and provider APIs. Triggers: model routing, model selection, reasoning effort, approved fallback, cost, escalation.
- allowed-tools
- Read
- effort
- medium
- user-invocable
- false
Model Routing Patterns
Choose routes from measured quality, latency and cost under the user's approved model and spending policy. An explicit model choice overrides automatic routing. This skill never authorizes a model-tier, permission or budget change.
Apply the same policy across Codex, Copilot and Claude: retain the model selected
by the native client. Provider API IDs, editor picker labels and agent aliases
are separate namespaces; do not translate between them by resemblance. For a
cross-provider application route, validate capabilities and availability on each
provider, and obtain authorization before transferring data or changing spend.
The project inventory is kb/reference/model-compatibility.md.
<!-- CLAUDE_CODE_ONLY_START -->Claude Code: available executors and supervised routing
Apply this section only in Claude Code. Other clients use their native agents and keep their configured models and reasoning effort. Never call the Claude Codex plugin from Codex, Antigravity or another client.
Check availability before choosing an executor. The Codex route requires all
three: the codex@openai-codex plugin is installed, effectively enabled for the
current project, and codex:codex-rescue is callable through the current Agent
tool. The toolkit SessionStart hint checks local metadata only; it does not
prove runtime availability, authentication, model access or security access.
An existing cache directory alone is insufficient. If the hint is absent,
verify those conditions from the client's plugin status and agent catalog.
When unavailable or disabled, use installed native agents with their configured models and effort. Do not install or enable a plugin, force a Codex command, or change the current session's model to satisfy this policy. If delegation itself is unavailable, do the authorized work in the current session and report that limitation. Explicit user model choices always take precedence.
The toolkit's Claude defaults use these roles when available:
| Work | Executor |
|---|---|
| Planning, coordination and acceptance | Native orchestrator, Opus high |
| Bounded implementation, tests and routine fixes | Native implementation agent, Sonnet high, or the available Codex plugin |
| Security work | Prefer Codex gpt-6-astra, xhigh; otherwise the installed native security agent and its configured model |
| Hard debugging | Available Codex at xhigh, or the native debugger, Opus xhigh |
Use Codex proactively for substantial independent implementation or diagnosis; do not require a failure first, and keep trivial edits with the current executor. Retain the native domain role, file ownership and review criteria when selecting the Codex executor. If Astra is unavailable, report that and use the configured native security agent. Do not silently select a different Codex model.
Dispatch with Agent(subagent_type="codex:codex-rescue", prompt="--fresh ...").
Include the task, working directory, owned paths, relevant evidence, acceptance
criteria and verification commands. Pass --model gpt-6-astra --effort xhigh
for the security route, and --effort xhigh for hard debugging. Ordinary coding
keeps the configured Codex model and effort unless the user chose otherwise.
These flags control the Codex worker, not the Sonnet forwarding wrapper.
Do not use the retired Spark alias or substitute a plugin command for the agent.
Request read-only work explicitly for audits or diagnosis; write access is appropriate only for an authorized implementation task. Codex's sandbox and approval restrictions still apply. Permission or authentication failures return to the supervisor; they do not authorize bypasses or a new account/provider. Selecting Astra does not load a security package or confer Trusted Access. Use an existing security package only when it is available in the delegated runtime and within the user's task; report which workflow actually ran.
The supervisor owns lifecycle and verification. A background job identifier is not completion: collect the final result using the plugin's documented status and result controls, keyed to that job. Resume only the identified prior task; use a fresh task for independent work. Empty output, failed startup and partial results are failures to resolve, not successful delegation. Do not redispatch failed writes until their partial changes have been inspected. Verify the diff, tests and required review before acceptance, then finish or cancel owned work. The forwarding wrapper must only forward; do not ask it to inspect or monitor.
When creating agents, keep native Claude model fields valid. Codex is a separate
executor, not a Claude model: value or an automatic Claude Team member. Reuse
the installed plugin instead of generating another wrapper or editing its cache.
<!-- CLAUDE_CODE_ONLY_END -->Show full SKILL.md (510 more words)Show less
Reviewed model reference (2026-10-01)
| Model | Claude API ID | API effort default |
|---|---|---|
| Claude Opus 5.5 | claude-opus-5-5 | medium |
| Claude Fable 5.1 | claude-fable-5-1 | high |
| Claude Sonnet 5.5 | claude-sonnet-5-5 | high |
| Claude Haiku 4.5 | claude-haiku-4-5-20251001 | Effort unsupported |
These are dated identifiers, not a runtime upgrade policy. Check the provider's model availability and current pricing before estimating costs. Do not encode universal cost ratios or declare a model best for every workload. Preserve a user-specified older model while supported; surface retirement or availability problems explicitly.
Effort and caching
Opus 5.5, Fable 5.1 and Sonnet 5.5 support low, medium, high, xhigh, and
max. Effort is a behavior control, not a hard spending cap. Opus 5.5 and Fable
5.1 use always-on adaptive thinking; a small output limit can truncate the answer.
Changing top-level output_config.effort invalidates message cache blocks, with
model-dependent effects on earlier caches. Supported per-message effort changes
can preserve the prefix. Do not assume effort tuning is cache-neutral.
Keep the configured agent/skill effort. An approved application experiment may compare effort settings, recording total thinking/output usage and completion quality at the same task budget.
Pattern 1: explicit task routing
Use application configuration reviewed for the workload. Labels such as "classification" or "architecture" are evaluation slices, not proof that one family is sufficient or necessary.
def choose_model(task, routes, allowed_models, explicit_model=None):
candidate = explicit_model if explicit_model is not None else routes.get(task)
if candidate is None or candidate not in allowed_models:
raise ValueError("No approved model for this request")
return candidateStart with the selected model. Add a separate classification call only when measured routing savings exceed its latency and token cost.
Pattern 2: validation-based escalation
Evaluate a result with task-specific checks: schema validation, failing tests, retrieval evidence, or human labels. A model's self-reported confidence is not a calibrated probability. Do not pass hidden reasoning between models; pass the problem, relevant evidence, and a short failure summary.
Escalate only along an approved route with a bounded attempt count. If no approved route remains, report failure or send the item for human review.
Pattern 3: delegation within configured roles
A planner can split independent tasks between workers when the task and client permit it. Use each agent's configured model and tools. Do not rewrite frontmatter or force a cheaper worker because a generic diagram suggests it.
Compare end-to-end quality and cost, including planning, handoffs and synthesis. More agents do not inherently save tokens.
Pattern 4: resilience fallback
Retry transient failures within the existing retry policy before considering a different model. The official SDK may already retry requests; avoid multiplying its retries with another unbounded loop.
A fallback must preserve the user's model requirement, context limits, structured output support and tool permissions. If changing models is not authorized, stop with the original model's error. Record every actual fallback and its reason.
Measuring
Track model ID, effort, policy version, attempts, latency, cache reads/writes and total billable tokens. Evaluate quality per task type and language using held-out examples. Set acceptance criteria before changing the route; do not use fixed confidence thresholds, traffic percentages or cost multipliers as universal rules.
Sources and related skills
Reviewed 2026-10-01:
- Claude model overview
- Effort
- Prompt caching
- Sonnet 5.5 prompting
- Codex models
- Astra model
- Models and Trusted Access
Use prompt-caching-patterns for cache design and json-mode-patterns for
structured results. Use the llm-ops-engineer agent for application routing.
© softspark, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in app/skills/model-routing-patterns of softspark/ai-toolkit.
Open the folder on GitHubat commit d64db2b
Compare with similar skills
Model Routing Patterns 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 Routing Patterns this skillsoftspark/ai-toolkit | 179 | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| 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 | |
| Model Routernidhi-singh02/agent-router | 110 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Codex Model Routing Teamzjp1997720/codex-model-routing-team | 158 | — | ~736 | Automated safety check: Pass | MIT | |
| Add Modelget-convex/convex-evals | 129 | — | ~1.5k | Automated safety check: Notes | Apache-2.0 |
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…
Model Router
nidhi-singh02/agent-router
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.
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.
Jev Route
cobusgreyling/Jev
Route with TypeSafe Jev — map Choice plus confidence to act/confirm/human, or pick a coding-agent model tier.
More from softspark/ai-toolkit
All 112 skills in this repoPrepare Test Env
softspark/ai-toolkit
Prepare or verify a project QA environment with source identity, readiness, browser access, evidence paths and owned cleanup.
A11y Validate
softspark/ai-toolkit
Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. An agent skill from softspark/ai-toolkit.
Analyze
softspark/ai-toolkit
Analyzes code quality, complexity, patterns across codebase.
Autonomous Dev
softspark/ai-toolkit
Drives a brief, specification, issue or existing PR through implementation, review, tests and QA to a ready PR.
Brand Voice
softspark/ai-toolkit
Direct technical voice for docs, README, user-facing text. An agent skill from softspark/ai-toolkit.
CI
softspark/ai-toolkit
Detect/generate/debug CI pipeline config (GitHub Actions, GitLab CI).
Related
Categories
Questions about Model Routing Patterns
What does Model Routing Patterns do?
Capability-aware model routing for Codex, Copilot, Claude and provider APIs. Model Routing Patterns is an agent skill from softspark/ai-toolkit. Capability-aware model routing for Codex, Copilot, Claude and provider APIs.
When should I use Model Routing Patterns?
Model Routing Patterns fits situations like: tasks that involve Model routing and gateways.
How do I install Model Routing Patterns in Claude Code?
Run `npx skills add softspark/ai-toolkit --skill model-routing-patterns -a claude-code`. Or copy the skill folder (app/skills/model-routing-patterns in softspark/ai-toolkit) into .claude/skills/model-routing-patterns in your project. Claude Code loads it when a task matches its description.
How do I install Model Routing Patterns in Codex?
Run `npx skills add softspark/ai-toolkit --skill model-routing-patterns -a codex`. Or copy the skill folder (app/skills/model-routing-patterns in softspark/ai-toolkit) into .agents/skills/model-routing-patterns in your project. Codex loads it when a task matches its description.
Can I use Model Routing Patterns 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 softspark/ai-toolkit --skill model-routing-patterns -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-routing-patterns, .gemini/skills/model-routing-patterns, .github/skills/model-routing-patterns and .opencode/skills/model-routing-patterns in your project.
What does Model Routing Patterns need to run?
SKILL.md names no scripts, command-line tools or credentials: Model Routing Patterns is instructions for the agent only. Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read.
Does Model Routing Patterns access the network?
SKILL.md names 3 domains. As links in the text: platform.claude.com, learn.chatgpt.com and developers.openai.com. This is read from the text; nothing was executed.
Is Model Routing Patterns 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 Routing Patterns use?
Model Routing Patterns is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Model Routing Patterns use?
About 2.4k tokens (SKILL.md is roughly 9.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Model Routing Patterns?
Skills that share tags, products or a category with Model Routing Patterns: Shogun Bloom Config (yohey-w/multi-agent-shogun, 1.4k stars), Codemie Analytics (codemie-ai/codemie-code, 294 stars), Model Router (nidhi-singh02/agent-router, 110 stars) and Codex Model Routing Team (zjp1997720/codex-model-routing-team, 158 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Model Routing Patterns?
softspark (a GitHub user) maintains it in softspark/ai-toolkit, which has 179 GitHub stars. The repository holds 112 skills in this directory. The repository was last updated on October 7, 2026.
Source: softspark/ai-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.