Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/linxule/memex-pluginnpx agentmods add commands/linxule/memex-plugin/statusWrote 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/linxule/memex-plugin/status)<a href="https://agentmods.dev/commands/linxule/memex-plugin/status"><img src="https://agentmods.dev/badge/commands/linxule/memex-plugin/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/linxule/memex-plugin/status"><img src="https://agentmods.dev/badge/commands/linxule/memex-plugin/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 | $0.00015 | $0.00778 |
| Opus 5.5 | $0.00006 | $0.00311 |
| Sonnet 5.5 | $0.00003 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Status Command
Display comprehensive status of the memex vault.
Instructions
-
Count files by type:
# Quick vault summary (if Obsidian is running) cd $(memex path) && uv run scripts/obsidian_cli.py status # Count memos find $(memex path)/projects -name "*.md" -path "*/memos/*" 2>/dev/null | wc -l # Count transcripts find $(memex path)/projects -name "*.md" -path "*/transcripts/*" 2>/dev/null | wc -l # Count topics (native CLI if available) cd $(memex path) && uv run scripts/obsidian_cli.py files --folder=topics --total 2>/dev/null || ls $(memex path)/topics/*.md 2>/dev/null | wc -l # List projects ls -d $(memex path)/projects/*/ 2>/dev/null | xargs -n1 basename -
Check pending memos (respects custom
state_dirfrom~/.memex/config.json):# `memex context` prints "Pending memos: N" only when N > 0; absent => 0 memex context 2>/dev/null | awk -F': ' '/^Pending memos:/ {print $2; found=1} END {if (!found) print 0}' -
Check index status:
memex index status -
Check condensation staleness (which projects have undigested memos):
for d in $(memex path)/projects/*/; do name=$(basename "$d") proj_md="$d/_project.md" count=$(find "$d/memos" -name "*.md" -newer "$proj_md" 2>/dev/null | wc -l | tr -d ' ') if [ "$count" -gt 0 ]; then condensed=$(grep -m1 'condensed:' "$proj_md" 2>/dev/null | awk '{print $2}') echo "$name: $count undigested memos (last condensed: ${condensed:-never})" fi done -
Get recent activity:
find $(memex path)/projects -name "*.md" -mtime -7 | head -10
For Obsidian CLI commands, prefix with cd $(memex path) &&.
Output Format
📊 Memex Status
Projects: 5
├── myproject (12 memos, 8 transcripts)
├── another-project (3 memos, 2 transcripts)
└── ...
Totals:
- 📝 Memos: 24
- 📜 Transcripts: 15
- 💡 Topics: 8
Search Index: ✅ Up to date (1.2 MB)
Condensation:
- memex: 14 undigested memos (last condensed: 2026-02-14)
- cognition: 4 undigested memos (last condensed: 2026-02-14)
- (other projects current)
⚠️ Pending: 2 memos failed to generate
Ask Claude to retry pending memos
Recent Activity (last 7 days):
- 3 new memos
- 5 sessions archived
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.
- 1mo ago First seen · 90 lines · 15 tokens per session scan A da04f6171928
status is a command published in the GitHub repository linxule/memex-plugin (7 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 778 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other commands, from other repositories
query
Query the wiki under one of three postures — research, contradictor, synthesis. Trigger FR — interroger le wiki, consulter le wiki, rechercher dans le wiki, contredire une thèse, synthétiser ce qu'on sait.
session-learn
Extract knowledge from the current session. Invoke with /session-learn or "extract this session".
setup
Configure mnemonic for proactive memory operations.
ingest
A command for adding information to a file-based knowledge wiki from web pages, files, or text notes. It classifies the material, updates or creates wiki pages, and adds links between related pages.
learn
Command "learn" from datacore-one/datacore, covering /learn, purpose, when to use, usage and quick capture.
evolve
Save knowledge to the cortex vault (Notes or Projects) and update index.