thaitype/skills · Archived

claude-context

Check context usage and session info for any Claude Code session. Use when the user asks about context usage, token count, session info, or wants to list/inspect Claude sessions.

First seen Aug 20, 2026

Installation

$ npx skills add thaitype/skills --skill claude-context

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from thaitype/skills · top by installs.

npx skills add thaitype/skills

Browse all from thaitype/skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 13
Default branch main
Open issues 0
Status Archived

Skill metadata

Parsed from SKILL.md frontmatter.

Declared agents claude-code

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,537 B
  • docs README.md 4,255 B
  • docs SUMMARY.md 200 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 2 installs

SKILL.md

Claude Context

Check context window usage for Claude Code sessions by reading .jsonl session files.

When to use

  • "how much context is this session using?"
  • "check context for session X"
  • "show session info for <id>"

Commands

# Show context summary for a session (falls back to $AGENT_SESSION_ID if no arg)
python3 .claude/skills/claude-context/scripts/session_summary.py <session-id>

# Use custom projects directory
python3 .claude/skills/claude-context/scripts/session_summary.py <session-id> --dir /path/to/projects

Output

The script shows:

  • Context used — tokens used vs context window (matches official /context)
  • Free space — remaining tokens
  • Autocompact buffer — 3.3% of context window reserved for auto-compaction
  • Session info — ID, project path, resume command
  • Last message — most recent user or assistant message

How context is calculated

Context used = the latest API call's inputtokens + cachereadinputtokens + cachecreationinput_tokens. This represents the total tokens sent to the model in the most recent turn, which equals the current context window usage.

After compaction (no new API call yet), the script estimates context from the compact summary size + system overhead (~18k) + post-compact messages.