sorting-hat
/sorting-hat
Audit and assign model tiers to every agent in the repo — classify each as planner, builder, or judge, and pin an explicit model per role so expensive models plan and judge while cheaper models execute. Use for "which agents should run on which model", "cut my token spend", "set up model tiers", "Opus is doing grunt work", or as part of /opus-pocus. Reports the classification table and the frontmatter edits; prescribes a lint so future agents must declare a tier. NOT for choosing the user's interactive session model — agents only.
- Author
- totes-mickgoats ↗
- Repository
- opus-pocus ↗
- Licence
- MIT
- Last repository change
- 09.08.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 09.08.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Audit and assign model tiers to every agent in the repo — classify each as planner, builder, or judge, and pin an explicit model per role so expensive models plan and judge while cheaper models execute. Use for "which agents should run on which model", "cut my token spend", "set up model tiers", "Opus is doing grunt work", or as part of /opus-pocus. Reports the classification table and the frontmatter edits; prescribes a lint so future agents must declare a tier. NOT for choosing the user's interactive session model — agents only.
Triggers from the description
Original author description
Audit and assign model tiers to every agent in the repo — classify each as planner, builder, or judge, and pin an explicit model per role so expensive models plan and judge while cheaper models execute. Use for "which agents should run on which model", "cut my token spend", "set up model tiers", "Opus is doing grunt work", or as part of /opus-pocus. Reports the classification table and the frontmatter edits; prescribes a lint so future agents must declare a tier. NOT for choosing the user's interactive session model — agents only.
How it works
- What to scan
- Classification
- When this spell has no subject
- Anti-patterns to find
- Fix prescriptions
- Bounds
- Report format
SKILL.md preview
--- name: sorting-hat description: Audit and assign model tiers to every agent in the repo — classify each as planner, builder, or judge, and pin an explicit model per role so expensive models plan and judge while cheaper models execute. Use for "which agents should run on which model", "cut my token spend", "set up model tiers", "Opus is doing grunt work", or as part of /opus-pocus. Reports the classification table and the frontmatter edits; prescribes a lint so future agents must declare a tier. NOT for choosing the user's interactive session model — agents only. --- # ✨ The Sorting Hat > *"Not every task deserves the expensive wizard. Opus plans, Sonnet toils, Haiku fetches — Opus returns to judge."* The thesis: use the top model as a **planner and judge, not an executor**. Architecture, decomposition, and final review reward the strongest model; mechanical execution mostly doesn't. An agent roster with no declared tiers runs everything on the session default — usually the most expensive model doing the least discriminating work. ## What to scan Every agent definition (`.claude/agents/*.md` and plugin agents), each one's `model:` frontmatter (or its absence), its tool set, and what its body actually asks it to do. ## Classification Read the agent's *task shape*, not its name: | Role | Task shape | Tier | |---|---|---| | **Judge** | Reviews, audits, refutes, grades; output is a verdict someone acts on; being wrong is expensive | Top model (Opus-class) | | **Planner** | Decomposes, architects, writes briefs others execute | Top model | | **Builder** | Writes code/content against a settled spec; correctness is checkable downstream (compiles, tests, lints) | Mid model (Sonnet-class) | | **Mechanical** | Renames, format fixes, lookups, file moves; a wrong answer is obvious and cheap | Small model (Haiku-class) | Edge rules: - An agent that both builds and self-reviews is a **builder** — the judging belongs in a separate judge pass, which is the whole point of the split. - Read-only auditors whose findings block a merge are **judges** even when cheap to run wrong — a plausible-but-wrong finding costs more than the model saved. - When genuinely torn, tier UP for verdict-producers, DOWN for artifact-producers. ## When this spell has no subject **Fewer than about five agents: report the classification table and stop.** Do not prescribe a decision record, do not prescribe a lint. Both are drift-control for a roster large enough to drift; on three agents the frontmatter *is* the policy, and a human reading three files *is* the enforcement. Prescribing governance for two lines of YAML is the scale inversion this book grades elsewhere. **A missing `model:` is not automatically a finding.** Inheriting the session model is the right call when the agent's cost is negligible, or when the user's plan may not grant the tier you would pin — a hard pin to a model the account cannot reach fails at dispatch, which is worse than an untiered agent. Flag a missing `model:` only when the agent is **frequently dispatched** *and* its role tier **differs from the session default**, and say which of the two you observed. ## Anti-patterns to find 1. **No `model:` on a frequently-dispatched agent whose tier differs from the session default** — it silently inherits whatever the session runs, which is the wrong tier by the roster's own classification. (On a small roster, or where the inherited tier is already correct, this is not a finding — see above.) 2. **Judge on a builder tier** (a reviewer pinned to a small model to save cost). 3. **Mechanical work on the top tier** (a rename bot inheriting Opus). 4. **Tier decided at dispatch time per call** — callers guess differently; the definition is the single source. 5. **No enforcement** — nothing makes the NEXT agent declare a tier, so the roster drifts back. ## Fix prescriptions - Emit the full classification table: agent · current model · role · prescribed model · one-line rationale. The user approves before edits. - Apply as `model:` frontmatter edits — one per agent definition. Use the **alias** (`opus` / `sonnet` / `haiku` / `inherit`), never a dated model ID: IDs age out and a stale one fails at dispatch. Where the account may not hold the top tier, prefer `inherit` for judges and pin only the down-tiers. - **On a roster of about five or more:** record the policy as a decision doc (ADR or equivalent) so the tiers are argued once, not re-litigated per agent. - **On a roster of about five or more:** add the lint — a wiring or CI check that every agent definition declares `model:`. The check, not the doc, is what keeps the roster sorted. Below that size the lint governs less than it costs. - Derived, never typed: if the repo documents the roster (a README table), generate the tier column from the frontmatter — a hand-typed copy drifts. ## Bounds - Scope: agent definitions and their frontmatter. Nothing else, and never the user's interactive session model. - Cap: the full classification table is the deliverable, so no cap applies — but findings (mis-tiered agents) rank at 15. - Done when every agent has been classified once. A repo with no agents gets `SCANNED NOTHING` and grades `N/A`, never `O`. - Quote once, at read time; mark anything you cannot re-confirm `UNVERIFIED` rather than re-reading to check yourself. - See `skills/opus-pocus/references/casting-safety.md` for the full rules. ## Report format The classification table, the count of agents changed per direction (up-tiered / down-tiered / newly declared), the estimated spend impact (which frequent agents moved down), and the lint status (exists / prescribed). `SCANNED NOTHING` if the repo has no agents.
Versions
The database has no other skills named sorting-hat.
Database snapshot: 13.11.2026 · package version e63969de2eb2 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100opus-pocus
The grand ritual — run the Opus Pocus audit passes over this repo's Claude instruction layer (memory files, hooks, skills, agents) and its automation layer, then emit The O.W.L. report with a grade per spell and a fix table you approve from. Triages first, so passes with no… - 100configure
Choose which Opus Pocus spells load in a session by writing per-skill `skillOverrides` entries to your settings, so a small repo carries three spells instead of all of them and pays only for what it uses. Detects the repo's shape, recommends a profile (greenfield / minimal /… - 90model-routing
Pick the right model per call, not per project — route Opus/Sonnet/Haiku, GPT-5/4o/mini, Gemini Pro/Flash by task, and cut cost without losing quality. Use when the user is choosing model tiers, building a router, or debating Opus-only vs mixed-tier deployments and mentions… - 100agent-builder
Creates Claude Code subagents (.claude/agents/*.md) and picks the best Claude model and effort level for each one (Haiku, Sonnet, Opus, or Fable) using cost, latency, and capability trade-offs. Also audits existing agents for over- or under-powered model choices and designs… - 100synthesis-model-tiers
Cross-provider model-tier convention: role labels judgment, routine and bulk resolved to model IDs per provider in tiers.yaml, routed by whether the cause is known. Use for model tiers, which model or effort level, model selection, switching models, model equivalents, or updating the model table. - 90model-tiers
This skill should be used when an orchestrator needs to choose or resolve a model for a delegated agent — i.e. by /bee:planner when authoring a plan (assigning a capability tier per agent per slice) and by /bee:plan-implementer when executing one (resolving a tier to a concrete…