@lh8ppl/claude-memory-kit 0.3.0 → 0.3.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: memory-search
3
- description: Searches the project's deep memory archive (claude-memory-kit) and returns a curated summary of relevant facts, decisions, and history. Use when the answer may already be recorded from a past session "what did we decide about X", "why did we do Y", "have we seen this error before", "how did we solve this last time", "what's our convention for Z" or before re-deriving any project knowledge, setup, or prior decision from the code. The session-start memory snapshot is a bounded hot index, not everything; this skill reaches the rest. Skip when the question is purely about current code state (use Read/Grep), about this conversation only, or the user asked to ignore memory.
3
+ description: Searches the project's recorded memory (claude-memory-kit) decisions, conventions, architecture, the reasoning behind choices, and where things live — and returns a curated, cited summary. Fire whenever the answer might be something the project already established in past work, HOWEVER the question is phrased any prior decision, convention, rationale, or "how/where/why is it this way" question, including oblique or roundabout asks ("why is everything so spread out?", "remind me what we settled on for X", "how come these files are tiny?"). Also fire when a "[claude-memory-kit] Memory available" hint appears on the prompt. The examples are illustrative, not a checklist — prefer recalling over re-deriving an answer from the code. The session-start snapshot is a bounded index; this skill reaches the rest. Skip only when the question is purely about uncommitted or just-edited live code that memory cannot know, concerns this conversation only, or the user asked to ignore memory.
4
4
  context: fork
5
5
  allowed-tools: mcp__cmk__mk_search mcp__cmk__mk_get mcp__cmk__mk_timeline mcp__cmk__mk_recent_activity Bash(cmk search *) Bash(cmk get *) Bash(cmk timeline *) Bash(cmk recent-activity *)
6
6
  ---
@@ -0,0 +1,16 @@
1
+ # claude-memory-kit — added by `cmk install`. Do not edit by hand;
2
+ # `cmk install` refreshes these lines idempotently. Remove via
3
+ # `cmk uninstall`.
4
+ #
5
+ # Force LF on the COMMITTED memory files. The kit's frontmatter parser uses
6
+ # a strict-LF boundary and split('\n') readers; default Windows git
7
+ # (autocrlf=true) rewrites line endings at clone, which made every fact
8
+ # invisible to search on a Windows checkout (D-126). The read side now
9
+ # self-heals (tolerant CRLF reads), but pinning LF here PREVENTS the
10
+ # mangling so it never has to.
11
+ #
12
+ # Scoped to the text extensions the kit actually commits (.md + .json) under
13
+ # context/ — NOT a blanket `context/** text`, so a future committed binary
14
+ # under context/ is never force-normalized + corrupted.
15
+ context/**/*.md text eol=lf
16
+ context/**/*.json text eol=lf
@@ -26,7 +26,7 @@ The `cmk doctor` health checks verify each layer is wired correctly: install int
26
26
 
27
27
  ### Recalling memory (for Claude)
28
28
 
29
- The snapshot injected at session start is a **bounded hot index, not everything** — there is a deeper, queryable archive. When a question is "what did we decide / what's our X / how does the user work / what's the setup," **query your memory instead of re-deriving the answer from scratch**:
29
+ The snapshot injected at session start is a **bounded hot index, not everything** — there is a deeper, queryable archive. When a question is "what did we decide / what's our X / how does the user work / what's the setup / **how is this project structured or built / where does X live / what's the architecture**," **query your memory instead of re-deriving the answer from scratch** — the structure is a recorded decision, recall it before re-reading the files to reconstruct it:
30
30
 
31
31
  - **`cmk search "<topic>"`** — find any captured fact (decisions, preferences, config, lessons) across the project + user tiers.
32
32
  - **`context/memory/<type>_<slug>.md`** — the granular fact archive with full **Why / How** rationale (`context/memory/INDEX.md` lists them).