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.
git clone --depth 1 https://github.com/loschenbd/claude-agent-boilerplateWrote 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/loschenbd/claude-agent-boilerplate/verify)<a href="https://agentmods.dev/commands/loschenbd/claude-agent-boilerplate/verify"><img src="https://agentmods.dev/badge/commands/loschenbd/claude-agent-boilerplate/verify/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/loschenbd/claude-agent-boilerplate/verify"><img src="https://agentmods.dev/badge/commands/loschenbd/claude-agent-boilerplate/verify.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 | $0.00000 | $0.00487 |
| Opus 5 | $0.00000 | $0.00244 |
| Sonnet 5 | $0.00000 | $0.00097 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
verify 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 5d 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
Run verification checks after an implementation to confirm a change works.
Instructions
This is the optional V-phase of QRSPI — verification after implementation, before declaring a task done.
- Identify project-appropriate verification commands. Check in this order:
CLAUDE.mdfor an explicit verification section.claude/agents/registry.md"Test policy" / quality conventionspackage.jsonscripts(look for:typecheck,lint,build,format:check,test)Cargo.toml,pyproject.toml,go.mod, etc. for non-JS projects
- Run the relevant commands sequentially via Bash. Stop on first failure for fast feedback.
- For each check, report:
- Command run
- Pass / fail
- Key output (file:line for failures, last 10 lines on errors)
- If all checks pass, summarize and recommend committing.
- If any fail, identify which specialist or manager owns the fix and recommend routing it back through the relevant team.
Default check order
- Type safety:
tsc --noEmitor the project's typecheck script - Lint: project's lint script (eslint, ruff, golangci-lint, etc.)
- Format: Prettier / formatter check (if configured to gate)
- Build: project's build script
- Tests: only run if the project has them. Many projects (per their CLAUDE.md / registry) skip automated tests.
Skip steps that don't apply (no TypeScript → skip typecheck).
Rules
- Don't fix anything. Verification is read-only — report failures, don't auto-fix.
- Be concise. Pass/fail summary plus failure details is enough; don't dump entire command output.
- Don't run a test suite the project says doesn't exist. Respect the registry's test policy.
- Surface flaky vs. real failures. If a check is known to flake (per CLAUDE.md), say so.
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.
- 5d ago First seen · 38 lines · 0 tokens per session scan A 166509321e5d
verify is a command published in the GitHub repository loschenbd/claude-agent-boilerplate (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 487 tokens. 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 2026-09-04.
Other commands, from other repositories
ci-setup
Setup CI pipeline from scratch. Creates GitHub Actions or GitLab CI configuration with lint, test, build, and deploy stages.
ship
Mechanical pre-deploy gate — tests, build, tree state.
coverage-diff
Run the local diff-coverage check that mirrors CI's Diff coverage required gate.
harness:cicd-fleet
Autonomous CI/CD-remediation orchestrator — triage the red CI/CD-run and flaky-test backlog by cause, fan out worktree-isolated subagents that run the real deflake/heal pipeline, independently verify each fix by artifact and deterministic all-OS CI, and hand back a batch of remediation PRs for one bulk human review.…
ship
Before merging or deploying, run ALL of the following checks. Every gate must pass.
test-setup
Scaffold test framework and CI pipeline.