Tier Injection

---
name: tier-injection
description: Installs the tier kit so a subagent runs on the model its tier names. Use when a host must pin the model of a spawn or a subagent ignores its tier.
---
<!-- Generated by `basicly skills-build` from skill.yaml. Do not edit; edit the source. -->

# Tier Injection

A subagent definition declares a portable `tier`: `low`, `medium`, `high` or `maximum`. The kit changes that tier into the model the spawn runs on, at spawn time.

## Rules

- **Check `CLAUDE_CODE_SUBAGENT_MODEL` first when a spawn ignores its tier.** It outranks the value the hook writes, and the hook stays silent.
- **Relaunch the whole CLI process after a first install.** The host does not watch a directory that did not exist at startup. `/clear` reloads neither hooks nor agents.
- **Remove a `model` pin to let the tier decide.** The hook leaves a definition that pins its own `model`, and a spawn that names one.
- **Commit `.basicly/core/models/model-map.json` in the repository.** A repository with no map in its own tree gets no rewrite.

## What the kit is

The kit is three files in `.basicly/core/kit/tier/`: `install_hook.py`, `claude_tier_hook.py` and `tier_resolver.py`. It needs no `basicly` import, nothing on `PATH`, no third-party package and no network. Copy the three files and `.basicly/core/models/model-map.json` into any repository, and the kit works there.

| Host | Result |
| --- | --- |
| Claude Code | A `PreToolUse` hook on the `Agent` tool |
| Copilot CLI | Nothing. Copilot selects the model of a subagent in its configuration, and the kit does not write that configuration |

## Install

```bash
python3 .basicly/core/kit/tier/install_hook.py --dry-run
python3 .basicly/core/kit/tier/install_hook.py
python3 .basicly/core/kit/tier/install_hook.py --user
```

A second run changes nothing. For every flag (`--user`, `--host`, `--root`, `--interpreter`, `--uninstall`) and the command each scope writes, read [install](references/install.md).

## Check a resolution without a spawn

```bash
python3 .basicly/core/kit/tier/tier_resolver.py --host claude --name my-agent
```

It exits 0 with a `model` and an `alias`, or exits 1 with the `reason` that nothing resolved. Other options: `--definition <path>`, `--tier <tier>`, `--default-tier <tier>`, `--vendor <vendor>`, `--map <path>` and `--root <path>`.

## Behaviour to expect

- The hook writes an alias such as `opus`, not a model id. The `model` field of the Agent tool takes an alias. The frontmatter of a definition takes a full model id.
- A tier that the map marks `unavailable` resolves to nothing, never to the model of another tier.

## When the repository requires tier-only dispatch

- A dispatch declares a tier: `low`, `medium`, `high` or `maximum`. It never names a provider model id; the tier kit's model map resolves the tier.
- Choose the tier by the cost per landed correct change: tokens, time and human interventions. A weak model's mistakes return as rework on the same change.
- Use `low` only for work whose wrong answer a check catches and a rerun fixes cheaply. Start implementation from prose, decomposition, design and costly judgements at `high`.
- A dispatch with no tier is a bug. It inherits the session's own model.