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.
npx skills add ngocsangyem/MeowKit --skill build-fixgit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/skills/ngocsangyem/meowkit/build-fix)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/build-fix"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/build-fix.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.01524 |
| Opus 5 | $0.00032 | $0.00762 |
| Sonnet 5 | $0.00013 | $0.00305 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade C, and why
mk:build-fix scanned grade C with 1 finding 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Different error output on cold vs warm cache means fixing the wrong error** — a first clean build often surfaces errors that incremental builds skip; fix errors only after a full clean build (`rm -rf dist .tsbuildinf How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Fix — Universal Build Error Resolver
Detects language from error output, loads the appropriate reference, classifies the error
by fixability, applies the fix, and chains into mk:verify to confirm the build is green.
When to Use
- Build command fails (npm run build, tsc, go build, python -m build, cargo build)
- Type check errors (TypeScript TS\d{4}, mypy)
- Compilation errors in any language
- Triggers: "build failed", "fix build", "compilation error", "type error"
Phase Anchor
Phase: 3 (Build GREEN)
Handoff: If mk:verify passes → proceed to Phase 4 (Review). If 3 attempts exhausted → escalate to user.
Process
Step 1: Capture Error Output
Run the failing build command and capture full output. If error output was passed as input, use that directly.
Step 2: Detect Language
Match error patterns in order (first match wins):
| Pattern | Language | Reference |
|---|---|---|
error TS\d{4}: |
TypeScript | references/typescript-errors.md |
SyntaxError: or ModuleNotFoundError: or IndentationError: |
Python | references/python-errors.md |
cannot find package or undefined: or syntax error near (Go) |
Go | references/general-errors.md |
error[E\d{4}] (Rust) |
Rust | references/general-errors.md |
| Any other pattern | Unknown | references/general-errors.md |
Load the matched reference file before proceeding to Step 3.
Step 3: Classify Error Fixability
After loading the reference, classify the error:
| Class | Description | Action |
|---|---|---|
| auto-fixable | Syntax errors, missing imports, simple type mismatches | Apply fix immediately |
| suggest-with-confidence | Wrong argument types, missing interface properties | Propose fix, apply after brief explanation |
| report-only | Runtime errors, architectural issues, circular dependencies | Describe the problem and root cause; do not auto-fix |
Auto-fixable examples: TS1005 Expected semicolon, TS2307 Cannot find module (missing import) Suggest-with-confidence examples: TS2322 type mismatch, TS2345 argument type mismatch Report-only examples: Circular dependency, architectural type mismatch requiring refactor
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 130 lines · 63 tokens per session scan C b79db6bae82f
mk:build-fix is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,524 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
investigate
Investigate bugs and errors in Elixir/Phoenix — root-cause analysis for crashes, exceptions, stack traces, test failures. Use --parallel for deep 4-track investigation.
narrow-bare-rescue
Narrow bare rescue in Elixir so real errors like KeyError and typos propagate instead of being swallowed. Use to audit rescues and refactor error handling.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.
phx-investigate
Investigate Elixir/Phoenix bugs root-cause first. Reproduce failures, cite evidence, and use optional Amp subagents only when useful.