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.
npx agentmods add commands/rohirik/openltm/admingit clone --depth 1 https://github.com/RohiRIK/OpenLtmWhat 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 | $0.00027 | $0.01356 |
| Opus 5 | $0.00014 | $0.00678 |
| Sonnet 5 | $0.00005 | $0.00271 |
| Haiku 4.5 | $0.00003 | $0.00136 |
Grade A, and why
admin scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parse the first word of the arguments as <subcommand>. Pass remaining words as <args>.
If no subcommand given, show:
Usage: /openltm:admin <subcommand>
migrate [status|up|down|reset|--legacy] — schema migrations + legacy DB detection
scan [--project X] [--dry-run] — scan memories for secrets and redact
server [start|stop|status] — LTM graph visualization server (port 7332)
audit [--memory-id N] [--op <op>] [--session <id>] [--since <iso>] [--limit N]
— query the memory write audit log
migrate
Manage versioned LTM schema migrations and legacy DB path migration.
| Arg | Action |
|---|---|
status (default) |
Show applied and pending migrations + check for legacy DB |
up |
Apply next pending migration |
down |
Rollback last applied migration |
reset |
Rollback ALL (requires confirmation) |
--legacy |
Trigger legacy ~/.claude/memory/openltm.db → plugin data migration |
bun run "${CLAUDE_PLUGIN_ROOT}/src/migrations.ts" --<arg>
For reset: ask user to confirm with "yes" before running.
After schema migration check, also detect legacy DB:
[ -f "$HOME/.claude/memory/openltm.db" ] && [ ! -f "$CLAUDE_PLUGIN_DATA/openltm.db" ] && echo "⚠ Legacy DB found at ~/.claude/memory/openltm.db. Run /openltm:admin migrate --legacy to migrate it."
When --legacy is the argument:
bun "${CLAUDE_PLUGIN_ROOT}/scripts/migrate-db.ts"
scan
⚠ Note: new memories are auto-scrubbed on write (via
db.ts). This scans existing memories only.
bun --eval "
import { Database } from 'bun:sqlite';
await (async () => {
const { scrubSecrets } = await import(process.env.CLAUDE_PLUGIN_ROOT + '/src/secretsScrubber.ts');
const args = process.argv.slice(2);
const dryRun = args.includes('--dry-run');
const project = args[args.indexOf('--project') + 1] ?? null;
const db = new Database(process.env.LTM_DB_PATH);
const where = project ? \"WHERE status='active' AND project_scope=?\" : \"WHERE status='active'\";
const rows = db.query('SELECT id, content FROM memories ' + where).all(...(project ? [project] : []));
let scanned = 0, redacted = 0;
const typeCounts = {};
for (const row of rows) {
scanned++;
const { scrubbed, redactions } = scrubSecrets(row.content);
if (redactions.length) {
redacted++;
redactions.forEach(r => typeCounts[r] = (typeCounts[r] ?? 0) + 1);
if (!dryRun) db.run('UPDATE memories SET content=? WHERE id=?', [scrubbed, row.id]);
else console.log('[dry-run] Memory ' + row.id + ' would redact: ' + redactions.join(', '));
}
}
const typeStr = Object.entries(typeCounts).map(([k,v]) => k+'('+v+')').join(', ');
console.log('Scanned ' + scanned + ', redacted ' + redacted + (typeStr ? ' ('+typeStr+')' : '') + (dryRun ? ' [dry-run]' : ''));
})();
" -- $@
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.
- 2d ago First seen · 129 lines · 27 tokens per session scan A 9a14810a8998
admin is a command published in the GitHub repository RohiRIK/OpenLtm (26 stars, last pushed 24d ago), licensed MIT. It adds 27 tokens to every session and 1,356 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.