cm
Build Persistent Agent Memory
AI coding agents lose useful lessons when sessions end. CM turns past work into reusable rules, warnings, and context for Claude, Codex, and Claude Code.
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "cm" from https://skillstore.io/skills/dicklesworthstone-cm.md and its manifest at https://skillstore.io/api/skills/dicklesworthstone-cm/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "cm". Get context for fixing an authentication timeout.
Expected outcome:
CM returns relevant rules about token expiry, past auth fixes, anti-pattern warnings, and suggested session searches.
Using "cm". Reflect on the last seven days of coding sessions.
Expected outcome:
CM summarizes repeated lessons, proposes new playbook entries, and flags weak rules that need validation.
Using "cm". Check safety guard status before running risky commands.
Expected outcome:
CM reports active trauma patterns, installed hooks, and commands that would be blocked or require review.
Security Audit
High RiskMost static findings are false positives from markdown code fences and inline command names. Confirmed risks are limited to user-initiated remote installer execution, sudo-based system installation, optional non-loopback server exposure, and sensitive agent session log processing.
Confirmed security concerns (2)
Capability review items (7)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚙️ External commands (50)
🌐 Network access (4)
📁 Filesystem access (17)
🔑 Env variables (4)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/dicklesworthstone-cm/audits/10?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/dicklesworthstone-cm?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/dicklesworthstone-cm?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/dicklesworthstone-cm/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/dicklesworthstone-cm.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
Dicklesworthstone. (2026). cm security audit report (audit version 10) [Author version unspecified]. Skillstore. https://skillstore.io/skills/dicklesworthstone-cm/audits/10BibTeX citation
@techreport{dicklesworthstone-dicklesworthstone-cm-2026,
author = {Dicklesworthstone},
title = {cm security audit report (audit version 10)},
institution = {Skillstore},
year = {2026},
number = {10},
url = {https://skillstore.io/skills/dicklesworthstone-cm/audits/10},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "cm security audit report (audit version 10)"
version: "unspecified"
type: report
authors:
- name: "Dicklesworthstone"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/dicklesworthstone-cm/audits/10"
identifiers:
- type: other
value: "skillstore:dicklesworthstone-cm:audit:10"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Reuse lessons across coding agents
Share successful debugging and architecture patterns between Claude Code, Codex, Cursor, and other agents.
Create team playbooks from real sessions
Turn repeated project decisions and fixes into rules that future agent sessions can retrieve.
Warn agents about past mistakes
Store harmful patterns and trauma guard rules so agents avoid repeating risky commands or bad approaches.
Try These Prompts
Use CM to get relevant rules for this task: fix the login timeout bug.
List the most relevant CM playbook rules for React testing and explain which ones apply today.
Mark the rule about mocking modules as harmful for this session because it caused a regression.
Analyze recent sessions, identify repeated security mistakes, and propose CM trauma guard patterns for the project.
Best Practices
- Run context retrieval before non-trivial tasks and keep result limits small.
- Review session privacy settings before enabling cross-agent enrichment.
- Mark rules helpful or harmful so confidence scores stay accurate.
Avoid
- Do not import sensitive session logs without consent and redaction review.
- Do not treat generated rules as permanent without feedback validation.
- Do not expose the MCP server beyond localhost without strong authentication.
Frequently Asked Questions
What does this skill do?
Which tools can use it?
Does it require cloud sync?
Can it work without LLM calls?
What data does it process?
What should users review before installing?
Developer Details
Author
DicklesworthstoneLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
1ffa7643651792ccb4bd3b15d924d2c97edff755
Maintenance freshness
7/18/2026
Usage
5 downloads · 182 views
File structure
📄 SKILL.md