andrem-sec/remember
.claude/skills/core/remember/SKILL.md
In-session memory tagging — mark content for recall later in the same session
$ install --global
skillsauthnpx skillsauth add andrem-sec/psc-comet rememberInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 24, 2026, 8:49 PM3.6s1 file scanned
SKILL.md
- name:
- remember
- description:
- When the tagged content becomes relevant later, surface it proactively
- version:
- 0.1.0
- level:
- 1
- context_files:
- []
- - name:
- Recall
Remember Skill
In-session memory tagging. Use <remember> tags to mark content Claude should actively recall later in the same session.
What Claude Gets Wrong Without This Skill
Claude processes context sequentially. Important constraints or decisions stated early in a session get deprioritized as new content fills the context window. By the time they are relevant, they are buried. The user has to repeat themselves.
<remember> tags are a signal to treat the tagged content as active working memory rather than archived history.
Usage
The user or Claude can invoke remember:
<remember>
We decided to use UUIDs not auto-increment IDs for this table.
The reason: cross-service portability.
</remember>
Or by invoking the skill:
Remember this: the auth service returns 429 instead of 401 on rate-limit — this is intentional.
Categories
| Category | What It Is |
|----------|-----------|
| decision | A choice made that affects downstream work |
| constraint | A limit that cannot be changed during this session |
| blocker | Something that will stop progress unless resolved |
| context | Background that makes a later question clearer |
| preference | User preference stated once that should persist |
Recall Behavior
When a remembered item becomes relevant to current work, surface it proactively:
Recall [decision]: We decided UUIDs not auto-increment. This affects the migration schema.
Do not wait for the user to re-state it.
Scope
<remember> tags are session-scoped. They do not persist to context/learnings.md unless explicitly promoted via lesson-gen or wrap-up.
Anti-Patterns
Do not tag everything as memorable. Overuse makes the signal meaningless.
Do not surface remembered items when they are not relevant — that is noise.
Mandatory Checklist
- Verify the tagged content was stated back to confirm it was captured
- Verify a category was assigned
- Verify the item will be surfaced proactively when relevant (not waiting to be asked)
Related Skills
andrem-sec/batch
data-ai
VerifiedTrustedCommunity
Parallel agent swarm — decomposes work into independent units, spawns isolated workers, tracks PRs via fan-in
1SKILL.mdUpdated Apr 16, 2026
andrem-sec/animation-safe
testing
VerifiedTrustedCommunity
Audit animations and transitions for motion accessibility, performance safety, and design intent. Enforces prefers-reduced-motion compliance and blocks layout-triggering transitions.
1SKILL.mdUpdated Apr 16, 2026
andrem-sec/ai-regression-testing
testing
VerifiedTrustedCommunity
Test specifically for AI-introduced regressions that repeat without tests
1SKILL.mdUpdated Apr 16, 2026
andrem-sec/agentic-engineering
development
VerifiedTrustedCommunity
Framework for decomposing agent-driven tasks into independently verifiable units
1SKILL.mdUpdated Apr 16, 2026