Borrowing it
Nothing to install: this file belongs to bakabaka91/claude-baton. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bakabaka91/claude-baton/main/.claude/commands/verify.mdgit clone --depth 1 https://github.com/bakabaka91/claude-batonWrote 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/bakabaka91/claude-baton/verify)<a href="https://agentmods.dev/commands/bakabaka91/claude-baton/verify"><img src="https://agentmods.dev/badge/commands/bakabaka91/claude-baton/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/bakabaka91/claude-baton/verify"><img src="https://agentmods.dev/badge/commands/bakabaka91/claude-baton/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 | $0.00290 |
| Opus 5.5 | $0.00000 | $0.00116 |
| Sonnet 5.5 | $0.00000 | $0.00058 |
| Haiku 4.5 | $0.00000 | $0.00029 |
Grade B, and why
verify scanned grade B 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
3. **Hook config:** Does setup add hooks to `~/.claude/settings.json`? What it actually says
Run through the acceptance verification checklist from PLAN.md.
Verification Checklist
Test each item and report PASS/FAIL with details:
- Package install: Can
npm pack && npm install -g *.tgzsucceed from the project root? - Setup: Does
claude-baton setupcreate~/.claude-baton/and init SQLite? - Hook config: Does setup add hooks to
~/.claude/settings.json? - Memory extraction: Start a session → Stop → are memories in SQLite?
- Search: Does
claude-baton search "test query"return relevant results? - CLAUDE.md sync: Does the managed block show constraints before decisions?
- Dead end check: Does
check_dead_ends("approach X")warn about known dead ends? - Daily summary: Does
daily_summary()generate a coherent summary?
For items that can't be tested yet (requires running MCP server with Claude Code), note them as SKIP with reason.
Report format
[PASS] 1. Package install — installed successfully
[FAIL] 2. Setup — ~/.claude-baton not created (error: ...)
[SKIP] 4. Memory extraction — requires live Claude Code session
Summary: X/8 PASS, Y/8 FAIL, Z/8 SKIP
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.
- 1mo ago First seen · 26 lines · 0 tokens per session scan B 929360e55e98
verify is a command published in the GitHub repository bakabaka91/claude-baton (25 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 290 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other commands, from other repositories
complete
Review implementation evidence and plan the spec completion transaction.
modernize-transform
Transform one legacy module to the target stack — idiomatic rewrite with behavior-equivalence tests.
test-bar
Generate a floating QA test overlay for the current branch's UI changes. Use when user says /test-bar, needs visual QA scenarios, or wants to test conditional rendering paths.
write-skill-test
RED-GREEN-REFACTOR implementation for writing-skills: Baseline testing, minimal skill writing, loophole closure, and full creation checklist.
verify
Run verification commands and confirm output before making success claims. Use before committing, creating PRs, or claiming work is complete. Evidence before assertions, ALWAYS.
speckit.tdd.plan
Derive the feature's test list by delegating to zfa tdd plan (deterministic engine); falls back to LLM-guided derivation only when zfa is unavailable.