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-inspect)<a href="https://agentmods.dev/commands/yakoub-ai/neural-memory/neural-inspect"><img src="https://agentmods.dev/badge/commands/yakoub-ai/neural-memory/neural-inspect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/yakoub-ai/neural-memory/neural-inspect"><img src="https://agentmods.dev/badge/commands/yakoub-ai/neural-memory/neural-inspect.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00463 |
| Opus 5 | $0.00000 | $0.00231 |
| Sonnet 5 | $0.00000 | $0.00093 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
neural-inspect 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 9d 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 — Deep Inspect
Deep-dive into a specific code element — see its full context in the knowledge graph.
What you get
- Full summary: Detailed explanation of purpose, logic, and interface
- Parent: Which module or class contains this
- Callers: Who calls this function (upstream)
- Callees: What this function calls (downstream)
- Siblings: Other functions/methods at the same level
- Children: Contained elements (methods in a class, etc.)
- Call chains: Trace execution paths up and down the graph
- Source code: The actual implementation (optional)
How to call
Via MCP tool (neural-memory configured as MCP server in Claude Code):
Tool: neural_inspect
{ "node_id": "module::ClassName.method_name" }
or by name:
{ "node_name": "method_name", "show_code": true, "trace_calls": true }
Via Python (working directly in the project):
import asyncio
from neural_memory.server import neural_inspect, InspectInput
# By node_id (most precise — get from neural_query results)
asyncio.run(neural_inspect(InspectInput(node_id="module::ClassName.method_name")))
# By name (fuzzy match)
asyncio.run(neural_inspect(InspectInput(node_name="method_name", show_code=True, trace_calls=True)))
Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
node_id |
str | None | Exact node ID from query results (most precise) |
node_name |
str | None | Name to fuzzy-search (use if you don't have the ID) |
project_root |
str | "." |
Project root directory |
show_code |
bool | false |
Include raw source code in output |
trace_calls |
bool | false |
Show full upstream/downstream call chains |
Provide either node_id or node_name — node_id is preferred when available.
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.
- 9d ago First seen · 49 lines · 0 tokens per session scan A 5b4b2bec48d6
neural-inspect 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 463 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
audit-release
Diagnose release-readiness against the Starter Series quality bar — matched starter, version-vs-last-tag drift, CHANGELOG drift vs merged PRs, and publish-workflow kind. Read-only.
repo-orch-deliberate
Adversarial multi-repo root-cause mode: spawn all repo specialists as an Agent Team, force them to challenge each other's assumptions with evidence, and surface the true cross-repo root cause of an incident. Max 3 deliberation rounds with a tie-break rule.
linkerd
Linkerd-specific diagnostics — mTLS verification, proxy injection issues, authorization policy debugging, traffic management, and multi-cluster connectivity problems.
debug
Systematic debugging with hypotheses and evidence gathering.
ia-report-bug
Report a bug in the whetstone plugin.
data-flow-analysis
Trace how data flows through the system from input to output.