phoenix-typescript

phoenix-typescript is a skill for Claude Code, Codex from All-The-Vibes/ATV-Phoenix. It costs 115 tokens per session (1,237 once invoked), scanned A, original, MIT.

A TypeScript workflow that treats the TypeScript checker as a required pass-or-fail check. TypeScript is JavaScript with optional checks that catch many mistakes before the program runs.

In plain words
What is it for?
Use it while editing TypeScript code, typically by running `tsc --noEmit` alongside tests to catch type errors before runtime.
Why use it?
It catches incorrect types early and discourages hiding errors with unsafe casts or ignore comments. A change is not considered complete until the checker reports no errors.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it while editing TypeScript code, typically by running tsc --noEmit alongside tests to catch type errors before runtime.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/all-the-vibes/atv-phoenix/phoenix-typescript
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.

Any agent
npx skills add All-The-Vibes/ATV-Phoenix --skill phoenix-typescript
Clone the repo
git clone --depth 1 https://github.com/All-The-Vibes/ATV-Phoenix

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 phoenix-typescript

README.md
[![agentmods](https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-typescript/github.svg)](https://agentmods.dev/skills/all-the-vibes/atv-phoenix/phoenix-typescript)
Your own site
<a href="https://agentmods.dev/skills/all-the-vibes/atv-phoenix/phoenix-typescript"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-typescript/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for phoenix-typescript

Your own site · 80×15
<a href="https://agentmods.dev/skills/all-the-vibes/atv-phoenix/phoenix-typescript"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-typescript.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,237 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00115 $0.01237
Opus 5 $0.00057 $0.00619
Sonnet 5 $0.00023 $0.00247
Haiku 4.5 $0.00012 $0.00124

Measured 10d ago against content hash 36b126546883, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

phoenix-typescript 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 10d 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/phoenix-typescript/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

phoenix-typescript — the type-checker is a phoenix_sense gate

Encodes Mat Pocock's / Total TypeScript philosophy: TypeScript wasn't built to make JS "strongly typed" — it was built to give JS a fast, powerful feedback loop. Phoenix treats that loop as a first-class objective check.

Overview

The TypeScript language server and tsc form exactly the kind of objective signal Phoenix runs on: you write code, the checker gives instant pass/fail, you adjust — all before runtime. So in Phoenix, tsc --noEmit is a phoenix_sense check, on equal footing with tests. A change isn't done because it "looks typed"; it's done when the type check is green.

The gate

{"check":{"kind":"command_exit","target":["npx","tsc","--noEmit"],"expect":0}}

Run it as the inner-loop check for any TS edit (alongside the test gate). Red tsc = not done.

The feedback loop

  edit .ts ──► tsc --noEmit (phoenix_sense) ──► ok? ──yes──► run tests ──► done
                     │                            no
                     ▼
              read the type error (DATA, not a nuisance)
                     │
                     ▼
              fix the TYPE, not @ts-ignore the symptom ──► re-sense

Craft rules (each keeps the gate meaningful)

  1. Work strict. "strict": true (and noUncheckedIndexedAccess) in tsconfig.json. Strictness is what makes the green check mean something; a loose config is a gate that can't fail.
  2. Kill any and unsafe casts. any disables the checker locally — it's a hole in the gate. Prefer unknown + narrowing. An as cast asserts a truth the compiler can't verify; treat every cast as a place a real bug can hide, and justify it.
  3. Derive, don't duplicate. One source of truth for a shape; derive the rest with typeof, indexed access (T["field"]), Parameters, ReturnType, Pick/Omit, as const. Duplicated types drift out of sync silently — exactly the failure types exist to prevent.
  4. Type the boundaries. Validate external/untrusted data (API responses, params) at the edge (a schema validator), so the typed core can trust its inputs. Inside, let inference do the work — don't annotate what TS already knows.
  5. No @ts-ignore / @ts-expect-error to pass the gate. Silencing the checker to get green is the TS equivalent of editing the test to match broken code. Fix the type. If a suppression is truly necessary, it needs a comment explaining why and a phoenix_sense test of the runtime behavior.

Read the full file on GitHub · 78 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. 10d ago First seen · 78 lines · 115 tokens per session scan A 36b126546883

Subscribe to this mod's changes

phoenix-typescript is a skill published in the GitHub repository All-The-Vibes/ATV-Phoenix (5 stars, last pushed 5d ago), licensed MIT. It adds 115 tokens to every session and 1,237 once invoked, about $0.0006 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.