coaltipple

A model-routing add-on for Claude Code that chooses whether a task should use a lower or higher model tier and effort level. It can delegate suitable work downward to save tokens or escalate harder work upward, including to a consent-gated top tier.

In plain words
What is it for?
Use it to route subagent tasks, balance cost against quality, set model-tier and effort choices, and apply routing through an advise-only hook.
Why use it?
It addresses the problem of choosing model quality and effort manually for every task. Its routing considers model rankings and avoids routing when the ranking state is invalid.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add TheColliery/CoalTipple
agentmods
npx agentmods add plugins/thecolliery/coaltipple/coaltipple
Clone the repo
git clone --depth 1 https://github.com/TheColliery/CoalTipple

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

coaltipple scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude-plugin/plugin.json · 24 lines

What it actually says

{
  "name": "coaltipple",
  "version": "1.5.1",
  "description": "CoalTipple — model/effort router for Claude Code. Delegates a task you CAN do but is large+cheap DOWN to a lower tier to save tokens; escalates a task beyond the current tier UP for quality — up to Fable 5, the top rung (a consent-gated, real-money spawn). Two-knob routing (tier × effort, effort-before-tier), an alias-floor tier ranking (haiku<sonnet<opus<fable + modelTiers pins) the platform resolves at spawn-time, a validity-gated ranking Lock that never routes on broken state, and git-optional damage control. Advise-only Phoenix-pure hook; the model performs the routing.",
  "author": {
    "name": "HetCreep"
  },
  "homepage": "https://github.com/TheColliery/CoalTipple",
  "repository": "https://github.com/TheColliery/CoalTipple",
  "license": "Apache-2.0",
  "keywords": [
    "model-routing",
    "effort",
    "delegation",
    "escalation",
    "token-optimization",
    "subagents",
    "model-classification",
    "router",
    "skills",
    "hooks"
  ]
}
Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 24 lines scan A e5ac4e6c5b7c

Subscribe to this mod's changes

coaltipple is a plugin published in the GitHub repository TheColliery/CoalTipple (6 stars, last pushed 3d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.