From subcog
Captures decisions, learnings, patterns, and context as persistent memories organized by namespace across Claude Code sessions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/subcog:memory-captureThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Capture decisions, learnings, patterns, and context as persistent memories that survive across sessions.
Capture decisions, learnings, patterns, and context as persistent memories that survive across sessions.
| Namespace | Use When | Signal Words |
|---|---|---|
decisions | Making architectural or design choices | "decided", "chose", "going with" |
patterns | Establishing recurring practices | "always", "never", "when X do Y" |
learnings | Discovering something new | "TIL", "gotcha", "discovered" |
context | Recording background information | "because", "constraint", "requirement" |
tech-debt | Noting future work | "TODO", "FIXME", "temporary" |
apis | Documenting API contracts | "endpoint", "API", "schema" |
config | Recording configuration details | "config", "environment", "setting" |
security | Security-related information | "auth", "vulnerability", "permission" |
performance | Performance insights | "optimization", "benchmark", "latency" |
testing | Testing strategies | "edge case", "fixture", "coverage" |
Capture Quality Guidelines:
For learnings:
[Discovery]: {what was learned}
[Situation]: {when/how it was discovered}
[Impact]: {why it matters}
For patterns:
[Pattern]: {the practice or convention}
[When]: {situations where it applies}
[Why]: {benefits of following this pattern}
Parameters:
namespace (required): One of the 10 namespacescontent (required): The memory contenttags (optional): Array of tags for discoverabilitysource (optional): Source reference (file path, URL, etc.)priority (optional): 1-5, higher = more importantReturns:
memory_id: Unique identifierurn: Memory URN for referencetimestamp: Capture time
npx claudepluginhub zircote/subcogStores important decisions, patterns, bug fixes, and lessons into Cortex persistent memory. Use after resolving bugs, making architecture choices, or when the user asks to remember something.
Persists learnings into a 5-layer memory hierarchy (CLAUDE.md files, memory/MEMORY.md) and consolidates by pruning outdated entries and promoting recurring patterns. Triggers on 'extract learnings', 'remember', 'dream'.