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/review-memorygit 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 | $0.00019 | $0.00535 |
| Opus 5 | $0.00010 | $0.00267 |
| Sonnet 5 | $0.00004 | $0.00107 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
review-memory 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
Maintenance runs offline and STAGES judgment calls (near-duplicate merges, summaries, evictions) as proposals; nothing changes in memory until a human approves. Walk the user through the queue and record only their explicit verdicts.
Hard rule — you may NOT decide any proposal on your own. Every approve / reject / edit / promote MUST come from an explicit user verdict in this conversation. If the user has not ruled on an item, leave it pending. A batch verb ("approve all exact dedups", "reject every eviction") is valid ONLY when the user says it in those words — never infer a batch decision from a single example or from silence. Silence is not consent; unreviewed proposals expire on their own.
Ask the user which namespace to review if they have not said. Then:
-
Fetch the queue. Call the
memory_review_queueMCP tool (namespace=<ns>, optionalkindindedup_near|summarize|evict,limit). It returns proposals grouped by subject entity, each carrying its evidence payload. -
Present, batched by entity and kind, with evidence. Show the before/after texts, cosine for near-dups, source facts for summaries, and the value signals for evictions. Keep it scannable so the user can rule quickly.
-
Collect explicit verdicts. Ask when a verdict is missing or ambiguous. Do not proceed on an item the user has not decided.
-
Decide per item the user ruled on. Call
memory_review_decide(namespace,proposal_id,decision, optionaledited_text) withdecisioninapprove|reject|edit|promote.edited_textapplies only to a summarize proposal the user chose to reword before approving.promoteis for lifting an eviction's fact back to the hot tier. -
Summarize. Report what was applied, what was rejected, and what remains pending (untouched, still awaiting the user).
Notes for the user:
- Approving is the only thing that changes stored memory. Rejecting leaves the spine byte-identical; ignoring a proposal lets it expire on its own.
- Use one namespace per project/session — the same guidance as the other memory commands.
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 · 46 lines · 19 tokens per session scan A 82189f81d0c8
review-memory is a command published in the GitHub repository Wuesteon/lean-memory (47 stars, last pushed 26d ago), licensed Apache-2.0. It adds 19 tokens to every session and 535 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
git
Git operations with intelligent commit messages and workflow optimization.
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.