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/search)<a href="https://agentmods.dev/commands/jubakitiashvili/context-mem/search"><img src="https://agentmods.dev/badge/commands/jubakitiashvili/context-mem/search/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/search"><img src="https://agentmods.dev/badge/commands/jubakitiashvili/context-mem/search.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 | $0.00018 | $0.00341 |
| Opus 5 | $0.00009 | $0.00170 |
| Sonnet 5 | $0.00004 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
search 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 9d 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
Search stored observations using context-mem's 4-layer search (BM25 + Trigram + Levenshtein + Vector).
Query the database directly using BM25 full-text search:
node -e "
const Database = require('better-sqlite3');
const db = new Database('.context-mem/store.db', { readonly: true });
const query = process.argv[1];
const sanitized = query.replace(/[^\w\s-]/g, '').split(/\s+/).filter(t => t).map(t => '\"' + t + '\"').join(' OR ');
const rows = db.prepare('SELECT o.id, o.type, substr(COALESCE(o.summary, o.content), 1, 200) as snippet, o.indexed_at FROM obs_fts f JOIN observations o ON o.rowid = f.rowid WHERE obs_fts MATCH ? ORDER BY bm25(obs_fts) LIMIT 10').all(sanitized);
rows.forEach((r, i) => console.log((i+1) + '. [' + r.type + '] ' + r.snippet.replace(/\n/g, ' ')));
if (!rows.length) console.log('No results found for: ' + query);
db.close();
" "ARGUMENTS"
Replace ARGUMENTS with the user's search query.
Present results clearly with type badges and snippets. If results are found, offer to show full content or /context-mem:status for more details.
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.
- 9d ago First seen · 28 lines · 18 tokens per session scan A c6470100fd43
search is a command published in the GitHub repository JubaKitiashvili/context-mem (19 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 341 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.