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 commands/adamw7/tools/module-buildgit 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 | $0.00015 | $0.00467 |
| Opus 5 | $0.00008 | $0.00234 |
| Sonnet 5 | $0.00003 | $0.00093 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
module-build 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 yesterday.
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
Build the module named in $ARGUMENTS, at the lifecycle phase it names (default
install).
mvn -pl <module> -am <phase>
-pl is always paired with -am. Without it the build fails before
compiling anything: the root pom's ReactorModuleConvergence rule rejects a
reactor whose modules' parents are absent from it, and sibling -SNAPSHOTs such
as mcp-common do not resolve from the local repository until they are
installed. If you see a missing parent or an unresolved sibling, that is this
mistake and not the module's code.
Resolve the module name against the root pom's <modules> before running
anything. Two are worth knowing:
codeis an aggregator; its real modules arecode/protogen-maven-plugin,code/protogen-maven-plugin-testandcode/context.data-testis deliberately outside the root reactor, so it is built from its own directory rather than with-pl.
If the request is really one test rather than a module, use one of these instead
— -Dtest applies to every module in the reactor, so surefire fails the upstream
ones where nothing matches:
cd <module> && mvn test -Dtest='SomeTest#someMethod'
mvn -pl <module> -am test -Dtest=SomeTest -Dsurefire.failIfNoSpecifiedTests=false
The first form needs mvn install -DskipTests to have run once, since a module
directory resolves its siblings from the local repository rather than the
reactor.
Add clean when the change removed a code-generation source, so a stale
generated builder in target/ cannot mask it.
Report the verdict and, on a failure, the module and test that failed with the assertion message — not the reactor summary.
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.
- yesterday First seen · 47 lines · 15 tokens per session scan A 64688fcbebce
module-build is a command published in the GitHub repository adamw7/tools (11 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 467 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
validate
You are the lead validation orchestrator for the Cobalt project. Your job is to prove that Cobalt implements every WhatsApp Web / Desktop / Mobile feature correctly, both at the source level (behavioral parity with the WA Web JS source) and at the observable level (the Nodes, WAM events and HTTP that Cobalt produces…
review
Review current changes for correctness, style, and potential issues.
refine-title
深度分析 Issue 或 PR 内容，并将其标题重构为 Conventional Commits 格式.
fit-analyze-codescan
分析 Code Scanning 告警并创建安全分析文档.
Review Code Structure
Audit class responsibilities, package boundaries, duplication, and rule compliance across Issues.
Fix Sonar Issues
Run local static analysis and fix findings with conservative, behavior-preserving changes.