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/linggen/linggen-memory/configgit clone --depth 1 https://github.com/linggen/linggen-memoryWhat 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 | $0.00029 | $0.00363 |
| Opus 5 | $0.00015 | $0.00181 |
| Sonnet 5 | $0.00006 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
config scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run the plugin's config script with the user's arguments and show its output verbatim:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/config.sh" $ARGUMENTS
The script does the work — read, probe, write, report. Do not re-implement any
of it, and do not edit client.json or settings.json yourself: a config write
is mechanical, and a model improvising a JSON edit is how a settings file gets
mangled.
Then, in one or two lines:
- If addresses changed, say restart Claude Code — MCP server URLs are resolved at startup, so this session still talks to the old ones.
- If a probe says
refused — needs a paired device token, the daemon is reachable but this machine isn't paired with it. Pair through Linggen on the machine that holds the store (its screen shows a code), then re-run with--token <token>. - If a probe says
no answer, nothing is listening there — on the local machine, the daemon may simply be down; on another machine,ling-memmust have been started with--hostto accept anything but loopback.
Usage the user may not know:
/linggen:config— show what is configured and probe it/linggen:config --ling-mem 192.168.1.5:9528 --token <t>— memory on another machine/linggen:config --local— back to this machine
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 · 33 lines · 29 tokens per session scan A 40a5d06e6e8b
config is a command published in the GitHub repository linggen/linggen-memory (108 stars, last pushed 13d ago), licensed MIT. It adds 29 tokens to every session and 363 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
implement-issue
You are orchestrating a Plan → Implement → Review → Remediate → PR cycle for a GitHub issue, with support for stacked PRs when issues form a linear dependency chain.
bm
Ask basemind anything about the current codebase — outlines, refs, callers, git history, blame, diffs, docs, memory.
bm-scan
Build or refresh the basemind index by running basemind scan via the CLI — works without the MCP server (use it when basemind reports "no index" / "no indexed files").
harden
Run the real-OSS harden harness against the 8 canary repos.
serve
Start the basemind MCP stdio server.
bm-doctor
Diagnose and recover basemind when it isn't working (MCP tools missing/erroring, "no index", dead server) — runs CLI checks and gives the client-specific way to reconnect the server.