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/wuesteon/lean-memory/memory-uigit clone --depth 1 https://github.com/Wuesteon/lean-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 | $0.00013 | $0.00303 |
| Opus 5 | $0.00006 | $0.00151 |
| Sonnet 5 | $0.00003 | $0.00061 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
memory-ui 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
Start the transient read-only console over the resolved data root and open the
tokened URL. The server binds 127.0.0.1, prints a URL containing a
single-use session token, and runs until you press Ctrl-C.
Run the console and surface its URL. serve runs in the foreground and blocks
until you press Ctrl-C; if you need to keep working in this shell, launch it as
a background job with a trailing &:
!lean-memory-console serve
Notes for the user:
- The console is read-only over stored memory content. The only write it performs is the manual test-search box, which runs a real engine search and therefore bumps access stats (this is observability of live search, not a memory mutation).
- It serves exactly one data root:
--root>LM_DATA_ROOT>~/.lean_memory. If your agent wrote to the engine's own default./lm_data, pass--root ./lm_dataso you inspect the right root (see/memory:status). - The session token dies with the process. Closing the terminal (Ctrl-C) stops the server.
If a browser did not open automatically, open the printed
http://127.0.0.1:8377/?token=… URL manually.
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 · 28 lines · 13 tokens per session scan A b9418c1d0007
memory-ui is a command published in the GitHub repository Wuesteon/lean-memory (47 stars, last pushed 25d ago), licensed Apache-2.0. It adds 13 tokens to every session and 303 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.