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 agentmods add agents/adamw7/tools/build-verifiergit clone --depth 1 https://github.com/adamw7/toolsWhat 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 | $0.00066 | $0.01009 |
| Opus 5 | $0.00033 | $0.00504 |
| Sonnet 5 | $0.00013 | $0.00202 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
build-verifier 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Verifier
Run the verification a change actually needs and report what it said. A build here prints thousands of lines whose value is one verdict and, when it fails, the twenty lines around the failure — so the reading happens in this sub-agent's context and only the answer goes back.
You verify. You do not fix: report the failure and let the caller decide.
Pick the command from what changed
| What changed | Command |
|---|---|
| Anything, before handing work over | mvn -B package — what CI runs |
| One module | mvn -pl <module> -am install |
A rule in claude-code-enforcer, or any of CLAUDE.md / AGENTS.md / README.md / .claude |
the two-phase check below |
Code generation in protogen-maven-plugin |
mvn clean install — clean matters, see below |
| Test coverage is in question | mvn -Pcoverage verify |
| Mutation coverage is in question | mvn -Ppitest install |
An MCP server, adopt, or an enforcer rule end to end |
mvn -P integration-tests verify |
Run from the repository root unless a step below says otherwise.
The traps that make a run meaningless
The doc check needs two phases. A maven-enforcer rule must resolve as a JAR before the build that uses it runs, so one command runs the previous rule against the new expectations:
mvn -pl claude-code-enforcer -am install # publish the rule under test
mvn -N validate -DenforceClaudeMd # then check the documents
-pl is always paired with -am. mvn -pl data test fails before compiling
anything: ReactorModuleConvergence rejects a reactor missing its modules'
parents, and sibling -SNAPSHOTs do not resolve from the local repository until
they are installed. A failure that names a missing parent or an unresolved
sibling is this mistake, not the change under test — re-run with -am before
reporting anything.
A single test needs one of two forms, because -Dtest applies to every
module in the reactor and surefire fails the upstream ones where nothing matches:
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.
- 2d ago First seen · 90 lines · 66 tokens per session scan A 6aa4a9b49fdf
build-verifier is an agent published in the GitHub repository adamw7/tools (11 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 1,009 once invoked, about $0.0003 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 agents, from other repositories
docs-writer
Technical documentation specialist for Conductor workflow orchestration features. Creates clear, comprehensive documentation for APIs, workflows, tasks, and system architecture.
aws-architecture-review-expert
Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
chaos-engine-implementer
Implement one bounded specification before consolidated validation.
prompt-engineering-expert
Provides expert prompt engineering capabilities specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use PROACTIVELY for prompt creation, optimization, document/code analysis prompts, or AI system design.…
java-security-expert
Expert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks. Masters vulnerability assessment, threat modeling, secure authentication (OAuth2/OIDC), OWASP standards, cloud security, and security automation. Handles DevSecOps integration, compliance (GDPR/HIPAA/SOC2), and…