model-inheritance

A rule requiring task subagents to use the same AI model as the main orchestrator. A task subagent is a helper agent launched to work on part of a request.

In plain words
What is it for?
Use it whenever the orchestrator starts or resumes task subagents, including during team work, debugging, research, reviews, and interactive sessions.
Why use it?
It prevents helper agents from silently running with a different model than the one selected for the main conversation.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/dentiny/kon/model-inheritance
Any agent
npx skills add dentiny/kon --skill model-inheritance
Clone the repo
git clone --depth 1 https://github.com/dentiny/kon

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 451 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.00451
Opus 5 $0.00016 $0.00226
Sonnet 5 $0.00007 $0.00090
Haiku 4.5 $0.00003 $0.00045

Measured 3d ago against content hash d9a609bc16bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

model-inheritance 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 3d 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.

skills/model-inheritance/SKILL.md · 53 lines

What it actually says

Model Inheritance

Owner: orchestrator
Consumers: all /kon:* commands that spawn Task subagents

Core principles (always): follow skills/core-principles — simplest correct spawn config; never omit model and hide the mismatch.

Problem

Cursor does not inherit the parent chat model on Task subagents. If you omit model, subagents often run on Composer while the orchestrator uses Opus, Sonnet, etc.

Per-agent model: lines in agents/*.md frontmatter are not applied to Task spawns — ignore them for model selection.

Rule

Every Task spawn and resume must pass model=<orchestrator slug>.

Use the same slug on resume passes (fix/re-review loops).

Resolve the slug

  1. Session (preferred) — recorded automatically from Cursor on each prompt:
MODEL=$(python3 $KON_ROOT/scripts/kon_session.py get-orchestrator-model --id "$SID")
  1. Your runtime — if the query above is empty, use the model slug from your Cursor session context (the model the user selected in the composer bar).

  2. OverridesKON_ORCHESTRATOR_MODEL env or ~/.kon/config.jsonorchestrator_model.

Task spawn example

Task(
  subagent_type="generalPurpose",
  model="<same slug as orchestrator>",
  prompt="Read agents/Azusa.md …",
  description="Azusa explore",
)

Do not rely on subagent_type="explore" alone — still pass model.

Verify

After spawning, the subagent label in Cursor should match the orchestrator family (e.g. Opus 4.8 ↔ claude-opus-4-8-thinking-high), not Composer 2.5.

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. 3d ago First seen · 53 lines · 33 tokens per session scan A d9a609bc16bb

Subscribe to this mod's changes

model-inheritance is a skill published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 451 once invoked, about $0.0002 per session on Opus 5. 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens