agent-routing SKILL.md skillA
agent-routing from oaustegard/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add oaustegard/claude-skills/agent-routing@v2.8.0Pins v2.8.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- oaustegard/claude-skills
- Path
agent-routing/SKILL.md- Versions recorded
- 14
- Latest version
- v2.8.0, committed Nov 1, 2026
- First version recorded
- Jul 16, 2026
- Size
- 35,178 bytes
- Repository stars
- 158
- License
- MIT
Decide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe (evaluator-as-selector, stop on regression). Routes on measured cost-per-completed-task rather than per-token price, because a tier's token count varies more by task shape than price varies across tiers. Covers per-model effort semantics, the concision lever, cascade preconditions, context handoff, and watching a subagent fan-out live. Use when choosing a subagent's model or effort…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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 …
Read the whole file at its exact version.
How to install
mdr add oaustegard/claude-skills/agent-routing@sha256:1d214d13c6ca18d1The line at the top of this page pins the label v2.8.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_strtmpfeu5mja4fj)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 14 versions of this file, between Jul 16, 2026 and Nov 1, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v2.8.0 latest | 2026-11-01 | a6c399a | 35,178 B | A | view · diff |
| v2.7.2 | 2026-10-14 | 1092845 | 32,906 B | A | view · diff |
| v2.7.1 | 2026-10-12 | fa37da5 | 32,911 B | A | view · diff |
| v2.7.0 | 2026-10-12 | 68bc438 | 32,323 B | A | view · diff |
| v2.6.0 | 2026-10-11 | ac9e3b2 | 31,638 B | A | view · diff |
| v2.5.0 | 2026-10-09 | c662020 | 31,165 B | A | view · diff |
| v2.4.0 | 2026-10-07 | 4e31045 | 28,543 B | A | view · diff |
| v2.3.0 | 2026-09-29 | 20b75b2 | 23,547 B | A | view · diff |
| v2.2.0 | 2026-09-29 | 2cc22c6 | 22,313 B | A | view · diff |
| v2.1.0 | 2026-09-04 | aa42cd7 | 19,425 B | A | view · diff |
| v2.0.0 | 2026-08-18 | 705addc | 15,658 B | A | view · diff |
| v1.4.0 | 2026-08-16 | 27da81d | 13,097 B | A | view · diff |
| v1.3.0 | 2026-07-24 | 4118be3 | 11,798 B | A | view · diff |
| v1.2.0 | 2026-07-16 | 1ccd62f | 7,232 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (35178 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
oaustegard/claude-skills · 158 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_strtmpfeu5mja4fj GET https://markdownregistry.com/api/v1/resolve?ref=oaustegard/claude-skills/agent-routing GET https://markdownregistry.com/api/v1/blob/1d214d13c6ca18d1c1619bb0d636544b28a15694fea5ea32f521c09657b2f697
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from oaustegard/claude-skills
Every file in oaustegard/claude-skills