Borrowing it
Nothing to install: this file belongs to majiayu000/vibeguard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/majiayu000/vibeguard/main/.claude/commands/vibeguard/build-fix.mdgit clone --depth 1 https://github.com/majiayu000/vibeguardWrote 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/commands/majiayu000/vibeguard/build-fix)<a href="https://agentmods.dev/commands/majiayu000/vibeguard/build-fix"><img src="https://agentmods.dev/badge/commands/majiayu000/vibeguard/build-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.
<a href="https://agentmods.dev/commands/majiayu000/vibeguard/build-fix"><img src="https://agentmods.dev/badge/commands/majiayu000/vibeguard/build-fix.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 | $0.00028 | $0.00651 |
| Opus 5 | $0.00014 | $0.00326 |
| Sonnet 5 | $0.00006 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
VibeGuard: Build 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 9d 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
Core Concept
- The goal of build error fixing is to make the build pass, not to refactor the code
- Fix from the root cause, one fix may solve multiple errors
- Minimum change principle: only fix build errors, no additional improvements
Steps
-
Catch build errors
- If the user provides error information: parse directly
- If the user provides a build command: run the command to capture the output
- If no parameters: try to detect the project type and run the corresponding build command
- Rust:
cargo build 2>&1 - TypeScript:
npx tsc --noEmit 2>&1 - Go:
go build ./... 2>&1 - Python:
python -m py_compile <files> 2>&1
- Rust:
-
Parse error
- Extraction: file path, line number, error type, error message
- Group by files
- Identify dependencies between errors (A causes B)
-
Locate the root cause
- Read the source file involved in the error
- Distinguish between direct causes and root causes
- Multiple errors may originate from the same root cause → Prioritize fixing the root cause
-
Perform minimal repair
- Only fix build errors, no additional improvements (L5)
- Do not use
@ts-ignore/# type: ignore///nolintbypass - Bypass type errors without
any/as any - Solve problems that the standard library can solve without introducing new dependencies (U-06)
-
Verification
- Rerun the build command to confirm zero errors
- Run tests to confirm there are no regressions
- Run type check confirmed passed
-
Output repair report
## Build repair report ### Error summary - Total number of errors: N - Root factor: M - Number of files repaired: K ### Fix details | File:line number | Error | Fix | |-----------|------|------| | ... | ... | ... | ### verify - Build: Pass/Fail - Test: pass/fail
Guardrails
- Don't change code style in fix (U-07)
- Not fixing unrelated issues all at once (U-09)
- Must verify that the build passes after fixing
Reference
- Common rules:
rules/claude-rules/common/ - Language rules:
rules/claude-rules/<lang>/
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.
- 9d ago First seen · 76 lines · 28 tokens per session scan A 865ab609fe82
VibeGuard: Build Fix is a command published in the GitHub repository majiayu000/vibeguard (41 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 651 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.
Other commands, from other repositories
debug
Systematic debugging: root cause before any fix, one hypothesis at a time, and a three-strikes rule that questions the architecture instead of stacking patches.
lint
The canonical linter per ecosystem over your changes: findings are diagnoses you judge, fix, or explain.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524) — sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
investigate
Systematic root-cause debugging — find the cause before writing any fix.
optimize
Analyze and suggest performance improvements for code, queries, or systems.
system-audit
Deep infrastructure audit command. Comprehensively audits all Badi components across 9 checkpoints.