Memory SyncSAFE
High-performance AI coding agent CLI written in Rust with zero unsafe code
Overview
High-performance AI coding agent CLI written in Rust with zero unsafe code
46a2537504c9OBSERVED · 2026-10-10What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: memory-sync description: Memory Sync Skill --- # Memory Sync Skill How to manually sync learnings to memory systems after tasks. ## Dual Memory Architecture Ariff uses two complementary memory systems: - **mem0-memory-mcp** - AI-native semantic memory for quick recall - **obsidian-memory** - Structured vault for long-term knowledge ## Manual Sync Commands ### Quick Save to mem0 ``` Use mcp__mem0-memory-mcp__add_memory to store: - Task context and solution - Key learnings and gotchas - Useful commands discovered ``` ### Save to Obsidian ``` Use mcp__obsidian-memory__create_note with: - path: "tasks/YYYY-MM-DD-task-slug.md" - content: Structured task notes ``` ## Memory Entry Template ```markdown ## Task: [Brief Title] Date: [YYYY-MM-DD] Device: [hostname] ### Problem [What was the issue/request] ### Solution [How it was resolved] ### Key Learnings - [Learning 1] - [Learning 2] ### Related - Previous tasks: [links] - Documentation: [links] ``` ## Creating Agent Instructions When a mistake or pattern should be avoided in future: 1. Create instruction file at: ``` Ariff-code-config/instructions/[category]-[topic].instructions.md ``` 2. Use format: ```markdown --- description: [What this instruction prevents/ensures] applyTo: [glob pattern like **/*.py or **/canvas/**] --- # [Rule Title] ## Context [When this applies] ## Rule [What to do/not do] ## Example [Good vs bad example] ``` 3. Add to 00_INSTRUCTIONS_INDEX.md if significant ## Reconciliation If memories seem out of sync: 1. Query both systems for topic 2. Compare entries 3. Update older system with newer info 4. Remove duplicates with less detail ## When to Save Save memory when: - ✅ Task completed successfully - ✅ Discovered non-obvious solution - ✅ Made mistake worth remembering - ✅ Found useful tool/command - ✅ Clarified user preference Skip saving when: - ❌ Trivial task (simple file edit) - ❌ Already documented elsewhere - ❌ One-off unique situation
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
.beads/beads.jsonl
Gates applied: no_behavioural_pass.
46a2537504c9full audit observations/trust-audit/skill/dicklesworthstone__memory-sync.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 46a2537504c9 | SAFE | B | 89 | first audit |
Questions
What does the Memory Sync skill do?
High-performance AI coding agent CLI written in Rust with zero unsafe code
Is Memory Sync safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Memory Sync access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (46a2537504c9), read on 2026-10-10. The repository is watched, and a new audit runs when it changes — this is the first audit.