Skip to content
Agentmart
Submit a tool

neander-session-stats

Show token usage, cost estimate, duration, and file stats for a checkpoint or session.

Skill by neanderhq

IndexedMIT★ 2
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/neanderhq-neander-session-stats

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Show token usage, cost estimate, duration, and file stats for a checkpoint or session. Use when the user asks about costs, token usage, how long something took, or checkpoint metrics. Accepts checkpoint IDs (16-char hex) or session IDs (UUIDs).

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/neander-session-stats

What's inside

Skill name
neander-session-stats
Description
Show token usage, cost estimate, duration, and file stats for a checkpoint or session. Use when the user asks about costs, token usage, how long something took, or checkpoint metrics. Accepts checkpoint IDs (16-char hex) or session IDs (UUIDs).
License
MIT
Instructions
26 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • name: missing

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Checkpoint info

## Step 1: Run stats command

```
python3 __SCRIPTS_DIR__/parse_jsonl.py stats --checkpoint <checkpoint_id_or_session_id_or_path>
```

The `--checkpoint` flag accepts a checkpoint ID (16-char hex), a full session ID (UUID), a partial ID, or a full file path.

If the user said "current", use your own session ID from the conversation context.
If the user said "list", run `python3 __SCRIPTS_DIR__/parse_jsonl.py list --project <current working directory>` and ask the user to pick.

## Step 2: Output verbatim

Copy the ENTIRE output from step 1 and output it as a markdown code block.

**IMPORTANT — DO NOT IGNORE THESE RULES:**
- **DO NOT SUMMARIZE.** Output every single line exactly as-is.
- **DO NOT ADD COMMENTARY.** No analysis, no suggestions, just the output.
- **USE A CODE BLOCK.** Wrap the entire output in triple backticks so it renders as preformatted text.

This is a DISPLAY command, not an ANALYSIS command. Your only job is to show the raw output.

$ARGUMENTS

From neanderhq/neander_checkpoints, MIT.

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Mar 29, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from neanderhq

Cite this page

neander-session-stats skill. Agent Mart. https://agentmart.dev/skills/neanderhq-neander-session-stats (last updated 2026-10-24)