signaltree-schema

signaltree-schema is a skill for Claude Code, Codex from JBorgia/signaltree. It costs 84 tokens per session (1,906 once invoked), scanned A, original, Apache-2.0.

A validation add-on for SignalTree that checks individual fields against schemas from libraries such as Zod or Valibot. It reports errors without preventing state changes, and can also run asynchronous checks.

In plain words
What is it for?
Use it to attach validation rules to nested state fields, wildcard paths, or parent paths, read errors for one field or the whole state, and check whether the state is valid.
Why use it?
It gives applications a consistent way to find invalid values and outdated validation results while keeping validation separate from state updates.

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/jborgia/signaltree/schema
Any agent
npx skills add JBorgia/signaltree --skill schema
Clone the repo
git clone --depth 1 https://github.com/JBorgia/signaltree

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for signaltree-schema

README.md
[![agentmods](https://agentmods.dev/badge/skills/jborgia/signaltree/schema.svg)](https://agentmods.dev/skills/jborgia/signaltree/schema)
Your own site
<a href="https://agentmods.dev/skills/jborgia/signaltree/schema"><img src="https://agentmods.dev/badge/skills/jborgia/signaltree/schema.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,906 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 $0.00084 $0.01906
Opus 5 $0.00042 $0.00953
Sonnet 5 $0.00017 $0.00381
Haiku 4.5 $0.00008 $0.00191

Measured 5d ago against content hash b50bbee79608, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

signaltree-schema 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 5d 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.

docs/skills/using-signaltree/schema/SKILL.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using @signaltree/schema

Enhancer for schema-driven validation. Register StandardSchema-compatible schemas (Zod / Valibot / ArkType / Effect Schema / any StandardSchemaV1) against dotted leaf paths; read errors per path or in aggregate. Observe-only: never blocks writes. Async-first with a write-sequence guard that drops stale verdicts.

Install:

npm install @signaltree/schema @signaltree/core @standard-schema/spec
npm install zod   # or valibot, arktype, etc.

Peer: @signaltree/core ^9, @standard-schema/spec ^1, @angular/core ^20 || ^21.

Basic — sync leaf schemas

import { signalTree } from '@signaltree/core';
import { schemas } from '@signaltree/schema';
import { z } from 'zod';

interface State {
  user: { email: string; age: number };
}

const tree = signalTree<State>({ user: { email: '', age: 0 } }).with(
  schemas({
    schemas: {
      'user.email': z.string().email(),
      'user.age': z.number().int().min(0),
    },
  })
);

tree.$.user.email.set('not-an-email');
tree.schemas.errorsAt('user.email')(); // 'Invalid email'
tree.schemas.isValid(); // false

Async schemas — pending state + write-sequence guard

import { z } from 'zod';

const usernameSchema = z.string().refine(
  async (value) => {
    const r = await fetch(`/api/check-username?u=${value}`);
    return (await r.json()).available;
  },
  { message: 'Username taken' }
);

const tree = signalTree({ user: { username: '' } }).with(schemas({ schemas: { 'user.username': usernameSchema } }));

tree.$.user.username.set('jonathan');
tree.schemas.isPendingAt('user.username')(); // true (in flight)
// On settle:
tree.schemas.errorsAt('user.username')(); // null or 'Username taken'

The write-sequence guard drops stale verdicts. If a newer write arrives mid-flight, the older schema run is orphaned — its promise still resolves (we can't abort it), but its verdict is discarded.

Debounce validate() for I/O-bound schemas. Calling validate() per keystroke piles up orphaned network requests. Wrap in a debounce.

Read the full file on GitHub · 213 lines

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. 5d ago First seen · 213 lines · 84 tokens per session scan A b50bbee79608

Subscribe to this mod's changes

signaltree-schema is a skill published in the GitHub repository JBorgia/signaltree (22 stars, last pushed 14d ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,906 once invoked, about $0.0004 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 2026-08-30.

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