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.
git clone --depth 1 https://github.com/JubaKitiashvili/context-memWrote 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.
[](https://agentmods.dev/commands/jubakitiashvili/context-mem/context-mem-status)<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.
<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>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 | $0.00022 | $0.00576 |
| Opus 5 | $0.00011 | $0.00288 |
| Sonnet 5 | $0.00004 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00058 |
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.
What it actually says
Show the current session status including token estimation and session chain.
-
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(); " -
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]
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.
- 10d ago First seen · 66 lines · 22 tokens per session scan A 3385c38f504d
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.
Other commands, from other repositories
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
context-stats
Display context window usage and token statistics.
handoff
Create a handoff document for seamless session continuity.
capturar
Capturar ideas y notas sin interrumpir el flujo de trabajo. Usa cuando el usuario dice "capturar idea", "quick note", "nota rápida", "grab this", "take a note", "guardar idea", "note to self", "capture thought", "I should remember", "guardar esto". Guarda en memoria persistente sin romper el contexto actual.
check
Run mneme check against a file or proposed change.
context
Retrieve relevant decisions from project memory for the current task.