What is type-ignore:fix?

A skill for finding and fixing type errors that were hidden with ignore comments across a codebase. It can scan supported source files, delegate work by file, and run type checking afterward.

It helps clean up TypeScript, JavaScript, Python, Go, Rust, and Ruby projects. It is useful when removing batches of type-ignore, lint-disable, or similar comments.

Ignoring errors leaves the underlying type problem in the code. This workflow replaces those suppressions with actual fixes and reports what remains.

type-ignore:fix — Skill for Claude Code by bendrucker/claude

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 bendrucker/claude --skill fix

Clone the repo

git clone --depth 1 https://github.com/bendrucker/claude

Made for: Claude Code.

Or install type-ignore, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bendrucker/claude/fix/github.svg)](https://agentmods.dev/skills/bendrucker/claude/fix)

Your own site

<a href="https://agentmods.dev/skills/bendrucker/claude/fix"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/fix/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bendrucker/claude/fix"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 283 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.

Model	Per session	Once invoked
Fable 5.1	$0.00028	$0.00283
Opus 5.5	$0.00011	$0.00113
Sonnet 5.5	$0.00006	$0.00057
Haiku 4.5	$0.00003	$0.00028

Measured 2mo ago against content hash fcdaf722b508, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

type-ignore:fix 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 2mo 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.

plugins/type-ignore/skills/fix/SKILL.md · 36 lines

What it actually says

Type Ignore Fixer

Fix type errors instead of ignoring them.

Scope

$ARGUMENTS

If no scope provided, scan the entire codebase.

Type Ignores Found

!rg '@ts-ignore|@ts-expect-error|eslint-disable|biome-ignore|oxlint-disable|oxfmt-ignore|type:\s*ignore|noqa|pylint:\s*disable|//nolint|//lint:ignore|#\[allow\(' -g '*.{ts,tsx,js,jsx,py,go,rs,rb}' -l 2>/dev/null || echo "none found"

Process

For each file above, spawn a type-ignore:fixer agent with prompt: "Fix type ignores in <file_path>"
Run type checking to verify fixes
Report summary: files fixed, ignores resolved, issues remaining

Spawn agents in parallel via multiple Agent calls in a single message.

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.

2mo ago First seen · 36 lines · 28 tokens per session scan A fcdaf722b508

Subscribe to this mod's changes

type-ignore:fix is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 283 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.

Claude Code Debugging claude-code-plugin

type-ignore:fix next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
type-ignore:fixbendrucker/claude	Skill	18	today	MIT	A	28	Claude Code
release-itwondelai/skills	Skill	2.7k	7d ago	MIT	A	131	Claude Code, Codex
tidewave-integrationoliver-kriska/claude-elixir-phoenix	Skill	574	3d ago	MIT	A	38	Claude Code
analyzersmdt/the-startup	Skill	579	14d ago	MIT	A	96	Claude Code
anti-patternsavelikiy/great_cto	Skill	113	today	MIT	A	59	Claude Code
windows-compatsdsrss/code-graph-mcp	Skill	92	today	MIT	A	165	Claude Code, Codex
vigil-instrumenttonone-ai/tonone	Skill	77	today	MIT	A	61	Claude Code