neural-add-bug — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited neural-add-bug (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Manually create a bug node in the knowledge graph. Use this when you discover a bug during a session and want it indexed immediately, without waiting for a context log re-import.
Via MCP tool (neural-memory configured as MCP server in Claude Code):
Tool: neural_add_bug
{
"description": "What went wrong",
"severity": "high",
"file_path": "neural_memory/parser.py",
"line_start": 142,
"root_cause": "Off-by-one in slice index",
"fix_description": "Changed range(n) to range(n+1)"
}Via Python (working directly in the project):
import asyncio
from neural_memory.server import neural_add_bug, AddBugInput
asyncio.run(neural_add_bug(AddBugInput(
description="What went wrong",
severity="high",
file_path="neural_memory/parser.py",
line_start=142,
root_cause="Off-by-one in slice index",
fix_description="Changed range(n) to range(n+1)",
)))| Parameter | Required | Type | Description |
|---|---|---|---|
description | Yes | str | What went wrong (min 3 chars) |
severity | No | str | "low" / "medium" / "high" / "critical" (default: "medium") |
file_path | No | str | Source file this bug relates to |
line_start | No | int | Starting line number |
line_end | No | int | Ending line number |
root_cause | No | str | Root cause description |
fix_description | No | str | How it was or should be fixed |
project_root | No | str | Project root (default: ".") |
RELATES_TO edges/neural-query results alongside code nodes.claude/context-log-gotchas.md on every /neural-index~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.