A command that starts NanoClaw, an interactive AI assistant in a terminal. It keeps conversation history in named Markdown session files and can load selected skill context.

Use it to start a persistent agent session, switch between sessions, view or clear history, and optionally load specified skills.

It lets you resume an assistant conversation across restarts instead of losing the previous exchange.

claw — Command for Claude Code by RohitBind123/claude-setup

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/RohitBind123/claude-setup

agentmods

npx agentmods add commands/rohitbind123/claude-setup/claw

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/rohitbind123/claude-setup/claw/github.svg)](https://agentmods.dev/commands/rohitbind123/claude-setup/claw)

Your own site

<a href="https://agentmods.dev/commands/rohitbind123/claude-setup/claw"><img src="https://agentmods.dev/badge/commands/rohitbind123/claude-setup/claw/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/rohitbind123/claude-setup/claw"><img src="https://agentmods.dev/badge/commands/rohitbind123/claude-setup/claw.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 464 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00023	$0.00464
Opus 5.5	$0.00009	$0.00186
Sonnet 5.5	$0.00005	$0.00093
Haiku 4.5	$0.00002	$0.00046

Measured 1mo ago against content hash 8a6f9dce1b10, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claw 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 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.

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.

commands/claw.md · 80 lines

What it actually says

Claw Command

Start an interactive AI agent session that persists conversation history to disk and optionally loads ECC skill context.

Usage

node scripts/claw.js

Or via npm:

npm run claw

Environment Variables

Variable	Default	Description
`CLAW_SESSION`	`default`	Session name (alphanumeric + hyphens)
`CLAW_SKILLS`	(empty)	Comma-separated skill names to load as system context

REPL Commands

Inside the REPL, type these commands directly at the prompt:

/clear      Clear current session history
/history    Print full conversation history
/sessions   List all saved sessions
/help       Show available commands
exit        Quit the REPL

How It Works

Reads CLAW_SESSION env var to select a named session (default: default)
Loads conversation history from ~/.claude/claw/{session}.md
Optionally loads ECC skill context from CLAW_SKILLS env var
Enters a blocking prompt loop — each user message is sent to claude -p with full history
Responses are appended to the session file for persistence across restarts

Session Storage

Sessions are stored as Markdown files in ~/.claude/claw/:

~/.claude/claw/default.md
~/.claude/claw/my-project.md

Each turn is formatted as:

### [2025-01-15T10:30:00.000Z] User
What does this function do?
---
### [2025-01-15T10:30:05.000Z] Assistant
This function calculates...
---

Examples

# Start default session
node scripts/claw.js

# Named session
CLAW_SESSION=my-project node scripts/claw.js

# With skill context
CLAW_SKILLS=tdd-workflow,security-review node scripts/claw.js

Changes

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 · 80 lines · 23 tokens per session scan A 8a6f9dce1b10

Subscribe to this mod's changes

claw is a command published in the GitHub repository RohitBind123/claude-setup (2 stars, last pushed 6mo ago), licensed MIT. It adds 23 tokens to every session and 464 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Building agents

claw

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Claw Command

Usage

Environment Variables

REPL Commands

How It Works

Session Storage

Examples

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

converge

implement

speckit.bug.fix