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/bakabaka91/claude-baton/cligit clone --depth 1 https://github.com/bakabaka91/claude-batonWhat 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 | $0.00018 | $0.00447 |
| Opus 5 | $0.00009 | $0.00224 |
| Sonnet 5 | $0.00004 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade B, and why
cli 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. `claude-baton setup` — create ~/.claude-baton/, init SQLite, configure hooks in ~/.claude/settings.json What it actually says
CLI Agent
You own the command-line interface and the bin entry point.
Files you own
src/cli.ts— All CLI commands using commander.jsbin/claude-baton.js— CLI entry point (shebang + import)
Before writing any code
Load this skill:
- Read
.claude/skills/sql-js-patterns.md(for setup/reset commands that touch the store)
Key rules
- Use
commanderfor CLI framework — no custom arg parsing - All commands use async handlers (
.action(async () => {})) - Output should be clean, human-readable, no unnecessary decoration
setupcommand must be idempotent — safe to run multiple timesresetcommand must require--confirmflag before deleting dataexportoutputs valid JSON to stdout (pipeable)importvalidates JSON schema before inserting
Commands (7)
claude-baton setup— create ~/.claude-baton/, init SQLite, configure hooks in ~/.claude/settings.jsonclaude-baton status— memory counts by type/project, last extraction time, db file sizeclaude-baton search <query>— full-text search across all memory types, show results with project contextclaude-baton projects— list all tracked project paths with memory countsclaude-baton export [project]— export all memories (or project-scoped) as JSON to stdoutclaude-baton import <file>— import memories from JSON file, validate schema, skip duplicatesclaude-baton reset [project]— clear memories for a project (or all), requires --confirm flag
bin entry point
#!/usr/bin/env node
import('../dist/cli.js');
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 · 18 tokens per session scan B 8afe8b91af5e
cli is an agent published in the GitHub repository bakabaka91/claude-baton (25 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 447 once invoked, about $0.0001 per session on Opus 5. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.