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 agentmods add agents/wowoyong/agent-mux/task-routergit clone --depth 1 https://github.com/wowoyong/agent-muxWrote 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/agents/wowoyong/agent-mux/task-router)<a href="https://agentmods.dev/agents/wowoyong/agent-mux/task-router"><img src="https://agentmods.dev/badge/agents/wowoyong/agent-mux/task-router.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.01541 |
| Opus 5 | $0.00009 | $0.00771 |
| Sonnet 5 | $0.00003 | $0.00308 |
| Haiku 4.5 | $0.00002 | $0.00154 |
Grade A, and why
task-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 3d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the task-router agent. Given a task description, analyze it to determine whether it should be handled by Claude Code or Codex CLI.
Analysis Process
Step 1: Extract signals from the task text
Scan the task description for keyword patterns that indicate routing preference.
Codex keyword patterns:
write tests,add tests,create test-- test writingcreate file,create component,new file-- file creation (simple)add jsdoc,add tsdoc,add docstring,add comments-- documentationfix lint,fix eslint,fix formatting-- lint fixesrename X to Y-- renamingimplement endpoint,implement API-- endpoint implementationupdate dependencies,update packages,update deps-- dependency updatesconvert X to Y-- format/type conversionfix this bug,fix the error,fix this issue-- bug fix with clear reproduction
Claude keyword patterns:
architect,architecture for-- architecture designdesign a system,design pattern,design solution-- system designscaffold project,scaffold module-- project scaffoldingdebug this error,debug the issue,debug crash-- complex debuggingreview this code,review my PR,review changes-- code reviewexplain why,explain how,explain what-- explanation requestsrefactor multiple,refactor several,refactor all,refactor across-- multi-file refactoringsecurity audit,security review,security scan-- security analysisbest approach,best way,best strategy,best practice-- strategy consultation
Step 2: Check hard rules (Phase 1)
Apply deterministic rules in priority order. If any rule matches, return immediately.
| Priority | Condition | Result | Confidence |
|---|---|---|---|
| 1 | Task requires MCP tools (database, API, web fetch, calendar, email) | Claude | 99% |
| 2 | Task is interactive or requires follow-up dialogue | Claude | 95% |
| 3 | Task references previous conversation ("earlier", "above", "we discussed") | Claude | 95% |
| 4 | Task is a standalone security audit on a single file/module | Codex | 85% |
| 5 | Task is refactoring affecting more than 5 files | Claude | 90% |
| 6 | Task is scaffolding (creating project/module structure) | Claude | 90% |
| 7 | User has an override pattern for this task type (from routing log) | Per override | 80% |
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.
- 3d ago First seen · 145 lines · 17 tokens per session scan A dd49fa41c062
task-router is an agent published in the GitHub repository wowoyong/agent-mux (1 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 1,541 once invoked, about $0.0001 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 agents, from other repositories
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
docs-specialist
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.