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/scottrbk/forgetful/memory-exploregit clone --depth 1 https://github.com/ScottRBK/forgetfulWhat 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 | $0.00008 | $0.00610 |
| Opus 5 | $0.00004 | $0.00305 |
| Sonnet 5 | $0.00002 | $0.00122 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
memory-explore 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Explore
Perform deep knowledge graph traversal to find related memories, entities, and documents.
Query: $ARGUMENTS
Exploration Strategy
- Explore DEEPLY - follow links aggressively, expand entities, traverse relationships
- Be thorough - comprehensive exploration is valuable
- Track visited IDs to prevent cycles
- Surface only results relevant to the user's query in your final response
- Filter out tangential discoveries
Phase 1: Semantic Entry
Start with a semantic search:
execute_forgetful_tool("query_memory", {
"query": "$ARGUMENTS",
"query_context": "Deep exploration via /memory-explore command",
"k": 5,
"include_links": true,
"max_links_per_primary": 5
})
Collect all primary_memories and linked_memories.
Phase 2: Expand Memory Details
For each primary memory found, get full details:
execute_forgetful_tool("get_memory", {"memory_id": <id>})
Extract: document_ids, code_artifact_ids, project_ids, linked_memory_ids
Phase 3: Entity Discovery
For discovered project_ids, find related entities:
execute_forgetful_tool("list_entities", {"project_ids": [<ids>]})
Note: Entities can be explicitly linked to projects for organizational grouping using:
execute_forgetful_tool("link_entity_to_project", {"entity_id": <id>, "project_id": <id>})
Phase 4: Entity Relationships
For each relevant entity, get relationships:
execute_forgetful_tool("get_entity_relationships", {
"entity_id": <id>,
"direction": "both"
})
Phase 5: Entity-Linked Memories
For each entity, get linked memories:
execute_forgetful_tool("get_entity_memories", {"entity_id": <id>})
Fetch any new memories not already visited.
Response Format
After exploration, provide a structured summary:
Memories Found
Primary (N):
- [Title] (importance: X) - brief content snippet...
Linked (N):
- [Title] (importance: X) - connection type...
Entity-linked (N):
- [Title] - discovered via [Entity Name]...
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 · 117 lines · 8 tokens per session scan A 0569a7290aa9
memory-explore is a command published in the GitHub repository ScottRBK/forgetful (296 stars, last pushed 7d ago), licensed MIT. It adds 8 tokens to every session and 610 once invoked, about $0.0000 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
release
Prepare a release by updating docs and bumping the version.
everme-help
Print a concise EverMe plugin status + reference card.
issue-verify
Run all requiredchecks for the active issue and record the verified receipt.
save
Save a key-value memory entry to persistent storage.
health
Run diagnostics on Nemp Memory health and integrity.
log
View memory access log (reads, writes, deletes).