context-mem-status

context-mem-status is a command for Claude Code from JubaKitiashvili/context-mem. It costs 22 tokens per session (576 once invoked), scanned A, original, MIT.

A command that reports the current coding-agent session's estimated token use, duration, observation count, and links to earlier sessions.

In plain words
What is it for?
Use it to check session resource usage, see how long the session has been running, count stored observations, and inspect its session chain.
Why use it?
Long agent sessions can make it difficult to know how much context has been used or whether work has continued from an earlier session. This gives those session details in one place.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the context-mem plugin — 1 skill, 6 commands, 5 hooks, 1 MCP server shipped together

Good fit Use it to check session resource usage, see how long the session has been running, count stored observations, and inspect its session chain.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jubakitiashvili/context-mem/context-mem-status
Install

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.

Clone the repo
git clone --depth 1 https://github.com/JubaKitiashvili/context-mem

Made for: Claude Code.

Or install context-mem, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 5 hooks, 1 MCP server.

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.

agentmods badge for context-mem-status

README.md
[![agentmods](https://agentmods.dev/badge/commands/jubakitiashvili/context-mem/context-mem-status/github.svg)](https://agentmods.dev/commands/jubakitiashvili/context-mem/context-mem-status)
Your own site
<a href="https://agentmods.dev/commands/jubakitiashvili/context-mem/context-mem-status"><img src="https://agentmods.dev/badge/commands/jubakitiashvili/context-mem/context-mem-status/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.

agentmods 80×15 button for context-mem-status

Your own site · 80×15
<a href="https://agentmods.dev/commands/jubakitiashvili/context-mem/context-mem-status"><img src="https://agentmods.dev/badge/commands/jubakitiashvili/context-mem/context-mem-status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 576 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00576
Opus 5 $0.00011 $0.00288
Sonnet 5 $0.00004 $0.00115
Haiku 4.5 $0.00002 $0.00058

Measured 10d ago against content hash 3385c38f504d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

context-mem-status 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 10d 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/context-mem-status.md · 66 lines

What it actually says

Show the current session status including token estimation and session chain.

  1. Query the database for session stats:

    node -e "
    const Database = require('better-sqlite3');
    const path = require('path');
    const db = new Database('.context-mem/store.db', { readonly: true });
    
    // Observations
    const obs = db.prepare('SELECT COUNT(*) as c FROM observations').get();
    
    // Token stats
    const stats = db.prepare('SELECT COALESCE(SUM(tokens_in),0) as used FROM token_stats').get();
    const limit = 1000000;
    const pct = Math.round((stats.used / limit) * 100);
    
    // Session chain
    let chainInfo = 'No chain data';
    try {
      const tableExists = db.prepare(\"SELECT name FROM sqlite_master WHERE type='table' AND name='session_chains'\").get();
      if (tableExists) {
        const chains = db.prepare('SELECT session_id, summary, token_estimate, created_at FROM session_chains WHERE project_path = ? ORDER BY created_at DESC LIMIT 5').all(process.cwd());
        if (chains.length) {
          chainInfo = chains.map((c, i) => {
            const label = i === 0 ? '(current)' : '';
            const tokens = c.token_estimate ? Math.round(c.token_estimate / 1000) + 'K' : '?';
            return c.session_id.slice(0,8) + ' ' + label + ' — ' + (c.summary || 'no summary') + ' [' + tokens + ' tokens]';
          }).join('\\n  ');
        }
      }
    } catch {}
    
    // Compactions
    const compactions = db.prepare(\"SELECT COUNT(*) as c FROM token_stats WHERE event_type = 'compaction'\").get();
    
    console.log(JSON.stringify({
      tokens_used: stats.used,
      tokens_limit: limit,
      tokens_pct: pct,
      observations: obs.c,
      compactions: compactions.c,
      chain: chainInfo
    }));
    db.close();
    "
    
  2. Present results in a clean format:

    context-mem session status
    ──────────────────────────
    Estimated tokens: ~340K / 1M (34%)
    Observations:     47 stored
    Compactions:      1
    Chain:
      abc12345 (current) — Session handoff design [340K tokens]
      def67890 — Multi-agent system, v1.4.0 release [280K tokens]
    
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.

  1. 10d ago First seen · 66 lines · 22 tokens per session scan A 3385c38f504d

Subscribe to this mod's changes

context-mem-status is a command published in the GitHub repository JubaKitiashvili/context-mem (19 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 576 once invoked, about $0.0001 per session on Opus 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 2026-08-30.