cm-continuity-c823f1 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited cm-continuity-c823f1 (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.
.cm/CONTINUITY.mdNeed to follow continuity correctly in normal day-to-day work?
└─ YES → Session Protocol
Need the template or expected CONTINUITY structure?
└─ YES → Continuity Template
Need to understand memory tiers, MCP bridge, URI scheme, or storage?
└─ YES → Load the relevant advanced reference
Need to audit memory quality and avoid stale/conflicting recall?
└─ YES → Memory Audit| Need | Summary | Load |
|---|---|---|
| Normal usage | start / during / end protocol | references/session-protocol.md |
| Template | CONTINUITY.md shape | references/continuity-template.md |
| Memory model | tiers, bus, long-term memory | references/memory-architecture.md |
| MCP bridge | context server tools and setup | references/mcp-context-server.md |
| URI lookup | cm:// resource references | references/cm-uri-scheme.md |
| Storage internals | learnings, decisions, formats | references/storage-formats.md |
| Memory audit | decay, conflict, reinforcement | references/memory-audit.md |
session-protocol.md for normal continuity use.memory-architecture.md only for advanced memory reasoning.mcp-context-server.md and cm-uri-scheme.md only for tooling/integration work.storage-formats.md only when editing persistence or migration logic.memory-audit.md only when reviewing memory quality or failure patterns.Use continuity every session. Load advanced memory details only when the task actually touches them.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.