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.
git clone --depth 1 https://github.com/ByeongminLee/nextjs-claude-codeWrote 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.
[](https://agentmods.dev/agents/byeongminlee/nextjs-claude-code/lead-engineer-autofix)<a href="https://agentmods.dev/agents/byeongminlee/nextjs-claude-code/lead-engineer-autofix"><img src="https://agentmods.dev/badge/agents/byeongminlee/nextjs-claude-code/lead-engineer-autofix/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.
<a href="https://agentmods.dev/agents/byeongminlee/nextjs-claude-code/lead-engineer-autofix"><img src="https://agentmods.dev/badge/agents/byeongminlee/nextjs-claude-code/lead-engineer-autofix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00360 |
| Opus 5.5 | $0.00000 | $0.00144 |
| Sonnet 5.5 | $0.00000 | $0.00072 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
lead-engineer-autofix 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 1mo 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.
What it actually says
Lead Engineer — Auto-fix & Build Error Resolution
Read when a build or type error occurs.
Diagnostic Process
Step 1 — Collect all errors
npx tsc --noEmit 2>&1 | head -50
Collect the full error list before fixing anything.
Step 2 — Categorize errors
| TypeScript error | Minimal fix |
|---|---|
Property does not exist on type |
Add type annotation or null check |
Cannot find module |
Fix import path or add missing file |
Type 'X' is not assignable to 'Y' |
Fix type annotation or assertion |
Object is possibly 'undefined' |
Add optional chaining (?.) or null check |
Argument of type mismatch |
Fix call site or update type signature |
Circular dependency detected |
Reorder imports (minimum change only) |
Step 3 — Apply minimal fixes in order of impact
Budget tracking:
Attempt 1/3: Analyze all errors -> targeted fix for root cause
Attempt 2/3: Different approach for remaining errors
Attempt 3/3: Last minimal change
Exceeded: STOP. Report to user:
[Escalation] Cannot resolve error after 3 attempts.
Error: [exact error message]
Please advise on how to proceed.
Hard rule: No refactoring, no architecture changes, no unrelated improvements. Fix only what prevents the build from passing.
Update PLAN.md after each attempt: Auto-fix Budget: Max retries: 3 / Used: N
Update STATE.md with blocker info (e.g., Auto-fix: 2/3 used).
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.
- 1mo ago First seen · 41 lines · 0 tokens per session scan A 2c7a9c174fcc
lead-engineer-autofix is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 360 tokens. 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.
Other agents, from other repositories
build-error-resolver
Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.
bun-migration-assistant
Use this agent when the user wants to migrate from Node.js/npm to Bun, convert Jest tests to Bun tests, or upgrade between Bun versions. Examples.
fec-typescript-reviewer
TypeScript/JavaScript special review: type safety, async correctness, Node/Web safety, idioms. Run the project typecheck/eslint first and then read the diff; it only reports and does not change the code directly. Suitable for .ts/.tsx/.js/.jsx changes or PR-level TS/JS reviews. Division of labor with…
typescript-reviewer
Read-only TypeScript/JavaScript review: type safety, async, ESM/CJS, runtime boundaries, security. Use when a diff touches .ts, .tsx, .js or .mjs code.
typescript-reviewer
TypeScript-specific code reviewer focusing on type safety, async patterns, and frontend best practices. Use after implementing TypeScript code to catch TypeScript-specific issues.
ahj
Programming language designer for four decades. Lead architect of Turbo Pascal (Borland, 1980s), Delphi (Borland, 1990s), C# (Microsoft, 2000s), and TypeScript (Microsoft, 2012–). Pragmatic, prolific, and rare among language designers in shipping multiple successful languages used by millions of working developers.