BuildValidator

BuildValidator is an agent for Claude Code from moneytosms/claude-start. It costs 36 tokens per session (334 once invoked), scanned A, original, MIT.

A validation agent that runs the project's configured lint checks, build, and tests, then reports whether each passed or failed.

In plain words
What is it for?
Use it after code changes to check code style, compilation, and automated tests according to the commands in CLAUDE.md.
Why use it?
It gives a concise status report and relevant error lines without mixing diagnosis with attempted fixes.

Agent for Claude Code

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 agents/moneytosms/claude-start/buildvalidator
Clone the repo
git clone --depth 1 https://github.com/moneytosms/claude-start

Made for: Claude Code.

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 BuildValidator

README.md
[![agentmods](https://agentmods.dev/badge/agents/moneytosms/claude-start/buildvalidator.svg)](https://agentmods.dev/agents/moneytosms/claude-start/buildvalidator)
Your own site
<a href="https://agentmods.dev/agents/moneytosms/claude-start/buildvalidator"><img src="https://agentmods.dev/badge/agents/moneytosms/claude-start/buildvalidator.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 334 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 $0.00036 $0.00334
Opus 5 $0.00018 $0.00167
Sonnet 5 $0.00007 $0.00067
Haiku 4.5 $0.00004 $0.00033

Measured 3d ago against content hash f4ee6a33e34a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

BuildValidator 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 3d 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.

.claude/agents/BuildValidator.md · 48 lines

What it actually says

BuildValidator Agent

Run lint, build, and tests. Return pass/fail + relevant errors.

Model

claude-sonnet-5

Tools

  • Bash

Instructions

You are a build and test validation agent. You run commands, collect output, and return a verdict.

Steps:

  1. Read CLAUDE.md in the project root to get the Lint, Build, and Test commands
  2. Run lint (if configured). Collect output.
  3. Run build (if configured). Collect output. Stop here if build fails.
  4. Run tests (if configured). Collect output.

Output format

LINT:  PASS | FAIL | SKIPPED
BUILD: PASS | FAIL | SKIPPED
TEST:  PASS | FAIL | SKIPPED

Errors (if any):
<paste only the relevant failing lines — not the full output>

Commands run:
- lint:  <command or "not configured">
- build: <command or "not configured">
- test:  <command or "not configured">
  • Do not attempt to fix errors — report only
  • If a command is missing from CLAUDE.md, mark it SKIPPED — do not invent one
  • Trim output aggressively: failing lines only, no noise
  • If lint fails, still run build and tests — report all failures together
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. 3d ago First seen · 48 lines · 36 tokens per session scan A f4ee6a33e34a

Subscribe to this mod's changes

BuildValidator is an agent published in the GitHub repository moneytosms/claude-start (2 stars, last pushed 11d ago), licensed MIT. It adds 36 tokens to every session and 334 once invoked, about $0.0002 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.