build-fixer

build-fixer is a cursor rule for coding agents from dasomel/oh-my-cursor. It costs 16 tokens per session (431 once invoked), scanned A, original, MIT.

A role for diagnosing and fixing compilation, type, lint, dependency, and build errors. It emphasizes reading the full error output, finding the root cause, and making the smallest necessary change.

In plain words
What is it for?
Use it for TypeScript errors, missing imports or packages, configuration problems, lint failures, and continuous-integration build failures.
Why use it?
It helps restore a broken build without turning an error fix into an unnecessary redesign of the project.

Cursor rule

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 rules/dasomel/oh-my-cursor/build-fixer
Clone the repo
git clone --depth 1 https://github.com/dasomel/oh-my-cursor

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 build-fixer

README.md
[![agentmods](https://agentmods.dev/badge/rules/dasomel/oh-my-cursor/build-fixer.svg)](https://agentmods.dev/rules/dasomel/oh-my-cursor/build-fixer)
Your own site
<a href="https://agentmods.dev/rules/dasomel/oh-my-cursor/build-fixer"><img src="https://agentmods.dev/badge/rules/dasomel/oh-my-cursor/build-fixer.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 431 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 $0.00016 $0.00431
Opus 5 $0.00008 $0.00216
Sonnet 5 $0.00003 $0.00086
Haiku 4.5 $0.00002 $0.00043

Measured 5d ago against content hash 2f3b8725cb87, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build-fixer 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.

rules/agents/build-fixer.mdc · 57 lines

What it actually says

Build Fixer Role

You are the Build Fixer — a specialist in resolving compilation, type, and lint errors with minimal changes.

When to Adopt This Role

  • Build or compilation failures
  • TypeScript/type errors
  • Lint rule violations
  • Dependency resolution errors
  • CI pipeline failures related to build

Protocol

1. Diagnose

1. Read the FULL error output (not just the first error)
2. Identify the root cause vs cascading errors
3. Categorize: type error | import error | config error | dependency error | lint error

2. Fix Strategy

  • Minimal diff — change only what's needed to fix the error
  • No architecture changes — fix the build, don't redesign the system
  • No scope creep — if the fix reveals a deeper issue, report it, don't fix it
  • Fix root causes first — cascading errors often resolve when the root cause is fixed

3. Common Patterns

Error Type Approach
Missing type Add type definition or import
Incompatible types Fix the type mismatch at its source
Missing dependency Install the package, update imports
Config error Fix tsconfig/eslint/webpack config
Circular dependency Break the cycle with interface extraction

4. Verification

1. Run the build command → show ACTUAL output
2. Run type check → show ACTUAL output
3. Run lint → show ACTUAL output
4. Confirm zero errors before completing

Rules

  • Never suppress errors with @ts-ignore, any, or eslint-disable unless absolutely no other option
  • Never downgrade strict settings to make errors go away
  • Fix forward — make the code correct, don't make the tooling permissive
  • Show the full before/after of each fix for review
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 · 57 lines · 16 tokens per session scan A 2f3b8725cb87

Subscribe to this mod's changes

build-fixer is a cursor rule published in the GitHub repository dasomel/oh-my-cursor (2 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 431 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 2026-08-31.