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 oaustegard/claude-skills --skill agent-routinggit clone --depth 1 https://github.com/oaustegard/claude-skillsWrote 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/oaustegard/claude-skills/agent-routing)<a href="https://agentmods.dev/skills/oaustegard/claude-skills/agent-routing"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/agent-routing/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/oaustegard/claude-skills/agent-routing"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/agent-routing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Output Handling · line 244 Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.Fix: Validate and sanitize all model output before using it in downstream contexts. Use parameterized queries for SQL, shell quoting for commands, and HTML encoding for web output.
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 | $0.00210 | $0.09596 |
| Opus 5.5 | $0.00084 | $0.03838 |
| Sonnet 5.5 | $0.00042 | $0.01919 |
| Haiku 4.5 | $0.00021 | $0.00960 |
Grade A, and why
agent-routing 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 6d 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 — 541 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Routing — model, effort, and cascade selection
Current prices, and what changed in 2026-10
| model | $/MTok in | out | cache read | one Agent-tool spawn, small seeded repo | one spawn, SWE-bench Verified |
|---|---|---|---|---|---|
| Haiku 5.5 | $0.10 | $0.50 | $0.01 | $0.005–0.011 | $0.024–0.037 |
| Sonnet 5.5 | $2 | $10 | $0.20 | $0.17 | $0.23–0.35 |
| Opus 5.5 | $4 | $20 | $0.20 | ~$0.34 (2× Sonnet, not measured) | — |
| Fable 5.1 | $10 | $50 | $0.25 | — | — |
Haiku 5.5 is 20× under Sonnet 5.5 on every token class (Haiku 4.5 was 2–5×), and its
prices hold for prompts up to 100K tokens ($0.50/$2.50 beyond). On the 14-repo
seeded-bug battery it solved 11/14 at rung 1, which is the pass set Sonnet 5.5 at low gets. With
the same-model informed retry it solved 14/14 for $0.12 in total, less than one Sonnet 5.5 spawn
(oaustegard/experiments → temporal-routing-headroom, 2026-10-07). Where the Haiku
4.5 figures below say Haiku loses on cost, rerun the arithmetic at 5.5 prices before
trusting them.
On real issues the picture holds with a smaller margin. Over 295 SWE-bench Verified tasks
(django and sympy) Haiku 5.5 resolved 256 (86.8%) at rung 1 for $7.06 in total. On its
39 misses, rung 2 with the failing tests' output resolved 30 retrying Haiku ($1.43) and
34 escalating to Sonnet 5.5 ($13.53). Sonnet solved every task the Haiku retry did and 4
more (p = 0.125) (oaustegard/experiments → swe-ladder, 2026-10-09). Real repair spawns
run longer than seeded ones, so a spawn costs 3–5× the small-repo figure on Haiku and
1.5–2× on Sonnet; the ratio between the tiers stays near 10×.
In Claude Code, price a subagent per spawn first. A fresh Agent-tool subagent writes a ~55K-token prefix (system prompt, tools, skills list) to the 5-minute cache on its first request. On short repair tasks that prefix outweighed everything the subagent produced: a Sonnet 5.5 spawn cost $0.17 input-side, 14× the $0.0121 output-only figure this skill used to quote per completed task. Same-model spawns in sequence share the cached prefix (reads cost 0.1×), so serialise spawns of one model when they can wait, and count spawns before counting output tokens. Every table further down prices output tokens only. That is still right for comparing tiers on long outputs, but it understates what a spawn costs.
What ships with it
4 files 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.
- 6d ago Changed · +31 lines 1d214d13c6ca
- 24d ago Changed dd83976e06f1
- 26d ago Changed · +8 lines 038d873a7b07
- 27d ago Changed · +8 lines · -12 tokens per session 2b475d42cecb
- 29d ago Changed · +39 lines · +1 tokens per session 722bb0e82ee3
- 1mo ago Changed · +73 lines · +24 tokens per session 7d59a2c89a13
- 1mo ago Changed · +60 lines · +9 tokens per session c1ac54d7d7e7
- 2mo ago Changed · +47 lines · +19 tokens per session c79a17c2dfa3
- 2mo ago First seen · 275 lines · 169 tokens per session scan A 8d6e979ed69c
agent-routing is a skill published in the GitHub repository oaustegard/claude-skills (158 stars, last pushed yesterday), licensed MIT. It adds 210 tokens to every session and 9,596 once invoked, about $0.0008 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.
agent-routing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-routingoaustegard/claude-skills | Skill | 158 | yesterday | MIT | A | 210 | Claude Code, Codex |
| superdesignsuperdesigndev/superdesign-skill | Skill | 963 | 2mo ago | MIT | A | 115 | Claude Code, Codex |
| figma-to-codescoobynko/claude-code-design-skills | Skill | 40 | 1mo ago | MIT | A | 0 | Claude Code, Codex |
| Linearwrsmith108/linear-claude-skill | Skill | 140 | 3mo ago | MIT | A | 32 | Claude Code |
| bpmn-xml-generatorstateway-io/bpmn-xml-generator | Skill | 4 | 13d ago | Apache-2.0 | A | 177 | Claude Code |
| smb-sales-boostTomsonx232/smb-sales-boost-skill | Skill | 5 | 25d ago | MIT | A | 200 | Claude Code, Codex |
| free-public-rest-apisaisenseapi/aisense-free-public-rest-apis | Skill | 1 | yesterday | MIT | A | 366 | Claude Code, Codex |