neural-tasks — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited neural-tasks (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.
Manage tasks across their full lifecycle: new → in_progress → testing → done → auto-archived.
Tasks are first-class citizens in the knowledge graph: they link to code nodes via RELATES_TO edges, appear in every prompt via the context hook, and are auto-archived when done.
| Status | Meaning |
|---|---|
new | Alias for pending — task not yet started |
pending | Task not yet started |
in_progress | Actively being worked on |
testing | Implementation done, under verification |
done | Complete — will be auto-archived at session end |
Tool: neural_list_tasks
{}Filter by status or priority:
Tool: neural_list_tasks
{ "status": "in_progress", "priority": "high" }Include archived tasks:
Tool: neural_list_tasks
{ "include_archived": true }Tool: neural_add_task
{
"title": "Implement caching for importance scores",
"phase_name": "Phase 3 — Performance",
"priority": "high",
"task_status": "in_progress",
"related_files": ["neural_memory/graph.py", "neural_memory/storage.py"]
}Use task_status: "new" or "pending" for not-yet-started tasks.
Update by task name (substring match) or node ID:
Tool: neural_update_task
{ "title_or_id": "caching", "task_status": "testing" }Update priority:
Tool: neural_update_task
{ "title_or_id": "caching", "priority": "high" }Add related files:
Tool: neural_update_task
{
"title_or_id": "caching",
"task_status": "done",
"related_files": ["neural_memory/embeddings.py"]
}| Parameter | Type | Default | Description |
|---|---|---|---|
status | str | null | Filter: pending, in_progress, testing, done |
priority | str | null | Filter: low, medium, high |
include_archived | bool | false | Include done/archived tasks |
project_root | str | "." | Project root |
| Parameter | Type | Default | Description |
|---|---|---|---|
title_or_id | str | required | Task name substring or full node ID |
task_status | str | null | New status: pending/new/in_progress/testing/done |
priority | str | null | New priority: low/medium/high |
related_files | list[str] | [] | Additional file paths to link |
project_root | str | "." | Project root |
| Parameter | Required | Type | Description |
|---|---|---|---|
title | Yes | str | Task title (min 3 chars) |
phase_name | No | str | Phase to attach this task to (auto-created if new) |
priority | No | str | "low" / "medium" / "high" (default: "medium") |
task_status | No | str | "new" / "pending" / "in_progress" / "testing" / "done" (default: "pending") |
related_files | No | list[str] | File paths this task relates to |
project_root | No | str | Project root (default: ".") |
Tasks integrate with the full neural-memory automation stack:
/neural-context needed)done tasks are auto-archived — no manual cleanup needed.claude/context-log-tasks-*.md on /neural-indexsession_context.md at session endphase_name if they don't existnew is accepted as an alias for pending in all toolsneural_update_task resolves by name substring — no need to know the exact node ID/neural-query to search tasks alongside code and bugs~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.