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.
git clone --depth 1 https://github.com/Yakoub-ai/neural-memoryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/yakoub-ai/neural-memory/neural-update)<a href="https://agentmods.dev/commands/yakoub-ai/neural-memory/neural-update"><img src="https://agentmods.dev/badge/commands/yakoub-ai/neural-memory/neural-update.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00000 | $0.00220 |
| Opus 5 | $0.00000 | $0.00110 |
| Sonnet 5 | $0.00000 | $0.00044 |
| Haiku 4.5 | $0.00000 | $0.00022 |
Grade A, and why
neural-update 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 8d 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
Neural Memory — Incremental Update
Sync neural memory with recent code changes without a full re-index.
What this does
- Checks git diff since last indexed commit
- Compares file hashes to detect modified files
- Re-parses only changed/added files
- Removes nodes for deleted files
- Re-resolves cross-file edges
- Recomputes importance scores
How to call
Via MCP tool (neural-memory configured as MCP server in Claude Code):
Tool: neural_update
{}
Via Python (working directly in the project):
import asyncio
from neural_memory.server import neural_update, UpdateInput
asyncio.run(neural_update(UpdateInput()))
UpdateInput has no required fields. Pass project_root="." to be explicit.
When to use
- After pulling new changes
- After a coding session with multiple file edits
- When
/neural-statusreports staleness
Much faster than a full index — only touches changed files.
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.
- 8d ago First seen · 37 lines · 0 tokens per session scan A 8340ef262ff8
neural-update is a command published in the GitHub repository Yakoub-ai/neural-memory (1 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 220 tokens. 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 2026-08-31.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
ccr
CCR (Compressed Context with Retrieval) — recall the full original of context that greatcto compressed/filtered out, by its short id. The retrieval half of the compression layer.
ai-act-ask
Answer an EU AI Act question grounded in the bundled knowledge base — verbatim statute text, obligation paraphrases, and the compound-risk taxonomy. Offline and deterministic by default; cites the articles it relies on.
broadcast
Run broadcast on a distilled Raw — update related existing pages conversationally.
check
Is the context layer still true? 0-token staleness + broken-citation audit (no LLM, CI-friendly). Add --status for the fast hash-only subset.