route SKILL.md skillA

route from jerseycheese/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jerseycheese/agent-skills/route@git:20261016.04e815b

Pins git:20261016.04e815b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jerseycheese/agent-skills
Path
skills/route/SKILL.md
Versions recorded
3
Latest version
git:20261016.04e815b, committed Oct 16, 2026
First version recorded
Sep 27, 2026
Size
7,226 bytes
Repository stars
3
License
MIT

Recommends which AI provider and model to run a task on, from your routing table and current subscription burn. Recommends only; never switches anything or starts the work. Trigger on: /route, "which model should I use", "where should I run this", "should I switch providers".

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

# Route

Recommend a provider and model for the task at hand. Recommend only. Never switch anything
automatically, and never start the work in place of answering.

Other skills call it too: `backlog-routing` asks it once per batch to pick a lane.

## Setup (once per machine)

The routing table and the budget tools are personal, so they live on your machine, not in this
repo.

| What | Where | If it's missing |
|---|---|---|
| Routing table | `$AI_ROUTING_TABLE`, default `~/.agents/ai-routing.md` | Stop and say so. Start one from `ai-routing.example.md` next to this skill. |
| Burn reader | `$AI_BUDGET_DIR/read-burn.sh --human` | Treat every seat's burn as unknown and say so. |
| Route logger | `$AI_BUDGET_DIR/log-route.sh` | Skip logging and say so once. |

The two scripts are yours to write, and both are optional. The skill only needs this much from
them:

- `read-burn.sh --human` prints one line per seat and window: provider, model or plan, window
  (5h or weekly), percent **used**, reset time, and the number's source (exact, estimate, STALE,
  or unknown).
- `log-route.sh <app> <phase> <recommended> [chosen]` appends one line with a timestamp to
  wherever you keep the log.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jerseycheese/agent-skills/route@sha256:ff12361440f3334c

The line at the top of this page pins the label git:20261016.04e815b, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_cedtk6xrstf2fnrz.svg)](https://markdownregistry.com/a/art_cedtk6xrstf2fnrz)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Sep 27, 2026 and Oct 16, 2026, about one every 9 days.

versioncommittedcommitsizeaudit
git:20261016.04e815b latest2026-10-16 04e815b 7,226 BA view · diff
git:20260927.a021ce32026-09-27 a021ce3 7,216 BA view · diff
git:20260927.78dd2742026-09-27 78dd274 6,418 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7226 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

GitHub

jerseycheese/agent-skills · 3 stars · license MIT · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_cedtk6xrstf2fnrz
GET https://markdownregistry.com/api/v1/resolve?ref=jerseycheese/agent-skills/route
GET https://markdownregistry.com/api/v1/blob/ff12361440f3334c0afe3f29f6a73827cb96db21ea1b4eb66672df91ed4d5f3f

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 jerseycheese/agent-skills

abstraction-finder SKILL.md skill
jerseycheese/agent-skills · skills/abstraction-finder/SKILL.md · Finds recurring patterns worth extracting into shared code and proposes the smallest form for each (helper, util, base…
git:20261016.04e815b · audit A · 3 stars
analyze-issue SKILL.md skill
jerseycheese/agent-skills · skills/analyze-issue/SKILL.md · Turns one GitHub issue into an implementation-ready tech spec: existing patterns, scope boundaries, a plan, and MVP…
git:20261016.04e815b · audit A · 3 stars
backlog-routing SKILL.md skill
jerseycheese/agent-skills · skills/backlog-routing/SKILL.md · Works a GitHub milestone with several agents at once: intake findings as issues, shape and batch the milestone, route…
git:20261019.0a6d7e4 · audit A · 3 stars
band-aid-finder SKILL.md skill
jerseycheese/agent-skills · skills/band-aid-finder/SKILL.md · Finds fixes that hide a symptom instead of fixing the cause, traces each to its root cause, and proposes the real fix…
git:20261016.04e815b · audit A · 3 stars
browser-debugger-cli SKILL.md skill
jerseycheese/agent-skills · skills/browser-debugger-cli/SKILL.md · Inspects live web pages through the Chrome DevTools Protocol with the `bdg` CLI: targeted DOM queries, computed styles…
git:20261016.04e815b · audit A · 3 stars
ci-fix-with-memory SKILL.md skill
jerseycheese/agent-skills · skills/ci-fix-with-memory/SKILL.md · Automatically invoke when CI checks fail on a PR. Do NOT wait for the user to ask; invoke as soon as a CI failure is…
git:20261016.04e815b · audit A · 3 stars
code-health-audit SKILL.md skill
jerseycheese/agent-skills · skills/code-health-audit/SKILL.md · Runs the "embarrassing code" / overengineering sweep and turns tech-debt anxiety into a short list of validated…
git:20261016.04e815b · audit A · 3 stars
comment-reaper SKILL.md skill
jerseycheese/agent-skills · skills/comment-reaper/SKILL.md · Finds and removes comments that add nothing: ones that restate the code, cite issue numbers, narrate refactor history…
git:20261016.04e815b · audit A · 3 stars
cyoa SKILL.md skill
jerseycheese/agent-skills · skills/cyoa/SKILL.md · Choose Your Own Adventure mode: frames a real dev task as a branching story where the user picks the design decision at…
git:20261016.04e815b · audit A · 3 stars
dead-code-cleanup SKILL.md skill
jerseycheese/agent-skills · skills/dead-code-cleanup/SKILL.md · Finds and removes dead or orphaned code, tests, and Storybook stories, including trivial tests that prove nothing…
git:20261016.04e815b · audit A · 3 stars
doc-rot SKILL.md skill
jerseycheese/agent-skills · skills/doc-rot/SKILL.md · Finds stale docs, comments, docstrings, and commented-out code, checks each against the actual code, then fixes or…
git:20261016.04e815b · audit A · 3 stars
drupal-mental-model SKILL.md skill
jerseycheese/agent-skills · skills/drupal-mental-model/SKILL.md · Explains code by mapping programming concepts to the Drupal equivalents Jack knows from years of Drupal and theming…
git:20261016.04e815b · audit A · 3 stars

Every file in jerseycheese/agent-skills

Other files named route

route SKILL.md skill
aiskillstore/marketplace · skills/0xrdan/route/SKILL.md · Manually route a query to the optimal Claude model (Haiku/Sonnet/Opus)
git:20260705.e9e4712 · audit A · 439 stars
route SKILL.md skill
jongwony/epistemic-protocols · route/skills/route/SKILL.md · The user meets the deficit their context shows as the protocol that resolves it and sees why, without recalling which…
git:20261015.672e932 · audit A · 173 stars
route SKILL.md skill
qwerfunch/cladding · skills/route/SKILL.md · Classify a natural-language prompt to one of cladding's verbs. Use when the user describes work in their own words and…
git:20260714.abe37cd · audit B · 16 stars
route SKILL.md skill
qwerfunch/cladding · plugins/codex/skills/route/SKILL.md · Classify a natural-language prompt to one of cladding's verbs. Use when the user describes work in their own words and…
git:20260714.abe37cd · audit B · 16 stars
route SKILL.md skill
qwerfunch/cladding · plugins/antigravity/skills/route/SKILL.md · Classify a natural-language prompt to one of cladding's verbs. Use when the user describes work in their own words and…
git:20260714.dac5b92 · audit B · 16 stars
route SKILL.md skill
technicalpickles/pickled-claude-plugins · plugins/second-brain/skills/route/SKILL.md · Analyze an enriched note and route to the best vault destination. Stage 3 of the processing pipeline.
git:20260615.ffd330d · audit A · 11 stars

Browse by kind, by grade A, or by owner.