القائمة
Query ctx memory and inject results into context
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Create or update the project security baseline, profile, suppressions file, and gitignore entries for security scans
Fix or guide remediation for a specific security finding from the latest scan report
Run a security assessment using deterministic static analysis tools with LLM-powered triage
Inspect and optionally install security scanning tools for the security plugin
Show ctx memory status (node counts, types, tiers, tokens)
MANDATORY persistent memory system for decisions, facts, patterns, and observations.
| name | recall |
| description | Query ctx memory and inject results into context |
| when_to_use | Searching for past decisions, facts, or patterns relevant to the current task |
| argument-hint | Query string, e.g. type:decision AND tag:project:myproject |
| user-invocable | true |
| allowed-tools | ["Bash"] |
Run a query against stored knowledge and present the results.
The user provides a query string as the argument. If no argument given, ask what they want to recall.
Run:
ctx recall "${ARGUMENTS}" --agent-out
Use --inject to queue results for injection at the next prompt-submit (useful when you want the knowledge available at the start of the next turn):
ctx recall "${ARGUMENTS}" --inject
Query syntax examples:
type:decision AND tag:project:myprojecttag:tier:referencetype:fact OR type:patternPresent the results clearly, showing node type, content, and tags for each match.