fix-types

A command that runs the project's type checker and fixes type errors with the smallest safe edits. A type checker finds cases where values or function inputs do not match the types expected by the code.

In plain words
What is it for?
Use it in TypeScript, Python, or Rust projects to detect the available checker, fix errors by file, and rerun the checks after each batch. It reports modified files and any errors left unresolved.
Why use it?
It reduces type errors without hiding them through broad escape hatches such as disabling checks. It compares the error count before and after the changes and stops when further progress would require a larger redesign.

Command

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 commands/juliusbrussee/caveman-code/fix-types
Clone the repo
git clone --depth 1 https://github.com/JuliusBrussee/caveman-code
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 270 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 $0.00017 $0.00270
Opus 5 $0.00009 $0.00135
Sonnet 5 $0.00003 $0.00054
Haiku 4.5 $0.00002 $0.00027

Measured 2d ago against content hash 1de24be80e6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fix-types 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.

packages/coding-agent/commands/fix-types.md · 33 lines

What it actually says

Fix type errors in the smallest, safest way.

  1. Detect the type-checker:
    • TypeScript projects: tsc --noEmit or tsgo -p tsconfig.json --noEmit.
    • Python: mypy or pyright.
    • Rust: cargo check.
  2. Run it once over the scope ${1:-.} and capture the error list.
  3. Group errors by file. Open the file with the most errors first, read it end-to-end, and apply minimal edits.
  4. Re-run the type-checker after each batch. Stop when:
    • All errors are gone, or
    • No further error reduction is possible without a wider refactor.
  5. Never silence errors with any, # type: ignore, @ts-ignore or equivalent unless there is no alternative; if you must, add a brief comment explaining why.

Report:

  • Errors before / after.
  • Files modified.
  • Any errors deliberately left and the reason.
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 · 33 lines · 17 tokens per session scan A 1de24be80e6e

Subscribe to this mod's changes

fix-types is a command published in the GitHub repository JuliusBrussee/caveman-code (929 stars, last pushed 18d ago), licensed MIT. It adds 17 tokens to every session and 270 once invoked, about $0.0001 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.