memory-usage
/memory-usage
Use when you need to query SiftCoder's persistent project memory across sessions. Provides MCP tools mem_search, mem_get, mem_timeline, mem_why, mem_drain. Triggers when the user asks "what did we decide about X", "why is X this way", "find prior discussion of X", "show me the history of Y".
- Author
- ialameh ↗
- Repository
- sift-coder ↗
- Licence
- MIT
- Last repository change
- 03.06.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 03.06.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Use when you need to query SiftCoder's persistent project memory across sessions. Provides MCP tools mem_search, mem_get, mem_timeline, mem_why, mem_drain. Triggers when the user asks "what did we decide about X", "why is X this way", "find prior discussion of X", "show me the history of Y".
Triggers from the description
Original author description
Use when you need to query SiftCoder's persistent project memory across sessions. Provides MCP tools mem_search, mem_get, mem_timeline, mem_why, mem_drain. Triggers when the user asks "what did we decide about X", "why is X this way", "find prior discussion of X", "show me the history of Y".
How it works
- Available MCP tools
- When to use which tool
- Patterns
- Anti-patterns
- Quick examples
SKILL.md preview
---
name: memory-usage
description: Use when you need to query SiftCoder's persistent project memory across sessions. Provides MCP tools mem_search, mem_get, mem_timeline, mem_why, mem_drain. Triggers when the user asks "what did we decide about X", "why is X this way", "find prior discussion of X", "show me the history of Y".
---
# Using SiftCoder Memory
SiftCoder runs a per-workspace memory daemon that captures tool observations, summarises them with a local or remote LLM, and exposes a queryable store with provenance.
## Available MCP tools
- `mem_search(query, k=10)` — hybrid BM25+vector retrieval, RRF fused, Ebbinghaus-decayed. Returns top-k summaries with timestamps and provenance hints.
- `mem_get(id)` — fetch full summary by id.
- `mem_timeline(id, before=5, after=5)` — chronological neighbours.
- `mem_why(id)` — BFS the provenance graph from a node and return the cause chain (`causes`, `derives_from`, `calls`, `imports`, `contradicts`, …).
- `mem_drain(batch=16)` — force a small drain pass (rarely needed; consolidator runs automatically).
## When to use which tool
| Intent | Tool |
|---|---|
| "Has this been discussed before?" | `mem_search` |
| "Show me that decision in full" | `mem_get` (after search) |
| "What happened around the time of X?" | `mem_timeline` |
| "Why did we end up with this code?" | `mem_why` |
| "I just made big changes, capture them now" | `mem_drain` |
## Patterns
**Always search before assuming.** If the user references prior work, run `mem_search` first. A hit is cheaper and more accurate than re-deriving from current files.
**Verify before acting on memory.** Memory is a snapshot of what was true when written. If it names a file/symbol/flag, grep or read first to confirm it still exists.
**Prefer `mem_why` over `git log` for non-obvious code.** `git log` shows the commit; `mem_why` shows the conversation that led to it.
**`mem_symbol_search` is recall, not live precision.** It finds symbols you have touched (regex-extracted, with provenance) — great for "where have I been." For live go-to-definition / find-all-references across a multi-language codebase, prefer Claude Code's code-intelligence (LSP) plugin. See `docs/foundations/large-codebases.md`.
**Don't dump raw mem_search results to the user.** Pick the 1–3 relevant ones, paraphrase, cite ids.
## Anti-patterns
- Do not use memory as the source of truth for ephemeral session state (tasks, todos, in-progress work). Use TodoWrite/TaskCreate for those.
- Do not write to memory directly — capture flows through hooks. If you want something pinned, surface it to the user and let them confirm.
## Quick examples
```
mem_search({ query: "auth middleware decision", k: 5 })
mem_get({ id: "summary:142" })
mem_why({ id: "summary:142" })
mem_timeline({ id: "summary:142", before: 3, after: 3 })
```
Versions
The database has no other skills named memory-usage.
Database snapshot: 13.11.2026 · package version 24cec5dbc209 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90siftcoder
Use as a meta-skill — "which SiftCoder skill should I use for X". Decision tree across families. Use when user is unsure which specific skill applies. - 100prompt
Use to craft a better prompt — for SiftCoder skills, for an LLM, or for a person. SiftCoder-aware framing. "Help me write a prompt", "rephrase this for the AI". - 90project-memory
Use when working in a repository that keeps durable project context, cross-session memory, incident history, decisions, or agent state across Claude, Codex, and later sessions. - 84memory
Store and retrieve durable agent memory — remember decisions, preferences, and session outcomes with calibrated salience; recall prior context before acting or resuming a project. Use whenever you store a memory, search memory, retrieve prior context, or check what was learned in past sessions. - 100persistent-memory
Give this agent durable memory across sessions using YantrikDB. Use at the start of every session to load prior context, whenever the user or a job references past decisions, people, preferences, or earlier runs, and whenever something worth keeping is learned (a decision, a… - 100auto-memory
This skill should be used when the user asks to 'set up memory', 'create memory files', 'create MEMORY.md', 'set up topic files', 'improve memory organization', 'what should I remember', 'how to structure memory files', 'MEMORY.md is too long', 'what goes in memory vs topic…