model-tiering SKILL.md skillA
model-tiering from prabhdeepsingh/claude-plugins is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add prabhdeepsingh/claude-plugins/model-tiering@git:20260913.4e5ade4Pins git:20260913.4e5ade4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- prabhdeepsingh/claude-plugins
- Path
sonu/skills/model-tiering/SKILL.md- Versions recorded
- 7
- Latest version
- git:20260913.4e5ade4, committed Sep 13, 2026
- First version recorded
- Jul 12, 2026
- Size
- 13,160 bytes
- Repository stars
- 4
- License
- MIT
Tag each plan step with the cheapest model tier that can execute it reliably, then delegate tagged steps to subagents at execution — keeping an orchestrator-class session clean for judgment, integration, and review. INVOKE when writing an implementation plan or executing one whose steps carry [delegate]/[delegate-heavy] tags; it locates its own tier and no-ops when no trustworthy tier sits below. Not for design-only exploration with no plan artifact.
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
# Model Tiering — route the work, keep the judgment A strong model's scarcest resource mid-build is clean context. Every mechanical, fully-specified step it executes itself dilutes the attention that architecture, integration, and review need — so the plan's author grades each step for the cheapest tier that can execute it reliably, and execution honors those grades with subagents. The motivation is quality via focus, not cost. The failure modes are symmetric, and the bar in Section 3 resolves both: doubt about any criterion keeps the work up; a step that clears all four goes down — hoarding it spends the exact context this skill exists to protect. ## How to apply this Locate your tier first — before any step is tagged (Section 1). Then the skill fires at two moments: - **While authoring a plan** — grade each step *in place* per Sections 2–4, tagging as you write. Don't defer tiering to a "who builds what" appendix: that retrofit framing is what produces all-or-nothing calls like "the session builds everything." - **While executing a plan** whose steps carry tags — honor them per Section 5. …
Read the whole file at its exact version.
How to install
mdr add prabhdeepsingh/claude-plugins/model-tiering@sha256:4ecc4b50b6ab52d4The line at the top of this page pins the label git:20260913.4e5ade4, 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_6wgrydckyyd2tzeq)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Jul 12, 2026 and Sep 13, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260913.4e5ade4 latest | 2026-09-13 | 4e5ade4 | 13,160 B | A | view · diff |
| git:20260909.6dfa821 | 2026-09-09 | 6dfa821 | 10,831 B | A | view · diff |
| git:20260826.0b4d903 | 2026-08-26 | 0b4d903 | 10,132 B | A | view · diff |
| git:20260825.06c64c5 | 2026-08-25 | 06c64c5 | 14,828 B | A | view · diff |
| git:20260729.94bdcd7 | 2026-07-29 | 94bdcd7 | 14,676 B | A | view · diff |
| git:20260712.828dff7 | 2026-07-12 | 828dff7 | 14,919 B | A | view · diff |
| git:20260712.fb3d336 | 2026-07-12 | fb3d336 | 12,454 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 (13160 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
prabhdeepsingh/claude-plugins · 4 stars · license MIT · pushed 2026-10-27 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6wgrydckyyd2tzeq GET https://markdownregistry.com/api/v1/resolve?ref=prabhdeepsingh/claude-plugins/model-tiering GET https://markdownregistry.com/api/v1/blob/4ecc4b50b6ab52d4407cdabb02364c2336ea702446b204b42b4ab22c1210b305
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.