PluginBench
Skill
Pass
Audit score 90

ck

affaan-m/ecc

Persistent per-project memory for Claude Code with auto-loaded context and git-aware session tracking.

What is ck?

Context Keeper maintains structured project memory across Claude Code sessions, auto-loading context on startup and tracking work via git activity. Use it to preserve project state, decisions, and next steps without manual context-switching.

  • Auto-loads project context on session start via SessionStart hook
  • Tracks session history with git activity detection
  • Saves session summaries, decisions, blockers, and next steps
  • Provides quick snapshots or full briefings of project state
  • Manages multiple projects with portfolio view
  • Migrates legacy v1 context data to v2 format

How to install ck

npx skills add null --skill ck
Prerequisites
  • Node.js installed
  • Claude Code with skill installation support
  • ~/.claude/settings.json configured with SessionStart hook
Claude Code
Cursor
Windsurf
Cline

How to use ck

  1. 1.Run `/ck:init` to register your current project and confirm auto-detected stack, goal, and constraints
  2. 2.Work on your project normally
  3. 3.Run `/ck:save` at session end to record summary, decisions, blockers, and next steps
  4. 4.Run `/ck:resume` or `/ck:info` at session start to load full briefing or quick snapshot
  5. 5.Use `/ck:list` to view all registered projects and switch between them
  6. 6.Run `/ck:forget [name]` to remove a project's context

Use cases

Good for
  • Resume multi-day projects without re-explaining context
  • Track architectural decisions and constraints across sessions
  • Identify blockers and next steps from previous work
  • Switch between multiple projects and recall each one's state
  • Preserve work progress when Claude Code sessions restart
Who it's for
  • Claude Code users managing long-running projects
  • Teams coordinating work across multiple sessions
  • Developers working on complex codebases requiring context retention

ck FAQ

What happens if I don't run `/ck:save` before closing?

The SessionStart hook will detect unsaved sessions and git activity on next startup, but you'll lose the structured summary, decisions, and blockers unless you save explicitly.

Can I edit context.json directly?

No — always use the `/ck:save` and `/ck:init` commands. Direct edits may break the data structure.

How do I migrate from v1 to v2?

Run `/ck:migrate --dry-run` first to preview changes, then `/ck:migrate` to convert all v1 CONTEXT.md and meta.json files. Originals are backed up.

What if my projects.json becomes corrupted?

The skill will detect malformation and offer to reset it to an empty object `{}`. You can then re-register projects.

Does this work across different machines?

No — context is stored locally in `~/.claude/ck/`. To share context, you'd need to manually export and merge context.json files.

Full instructions (SKILL.md)

Source of truth, from affaan-m/ecc.


name: ck description: Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions. metadata: origin: community version: 2.0.0 author: sreedhargs89 repo: https://github.com/sreedhargs89/context-keeper

ck — Context Keeper

You are the Context Keeper assistant. When the user invokes any /ck:* command, run the corresponding Node.js script and present its stdout to the user verbatim. Scripts live at: ~/.claude/skills/ck/commands/ (expand ~ with $HOME).


Data Layout

~/.claude/ck/
├── projects.json              ← path → {name, contextDir, lastUpdated}
└── contexts/<name>/
    ├── context.json           ← SOURCE OF TRUTH (structured JSON, v2)
    └── CONTEXT.md             ← generated view — do not hand-edit

Commands

/ck:init — Register a Project

node "$HOME/.claude/skills/ck/commands/init.mjs"

The script outputs JSON with auto-detected info. Present it as a confirmation draft:

Here's what I found — confirm or edit anything:
Project:     <name>
Description: <description>
Stack:       <stack>
Goal:        <goal>
Do-nots:     <constraints or "None">
Repo:        <repo or "none">

Wait for user approval. Apply any edits. Then pipe confirmed JSON to save.mjs --init:

echo '<confirmed-json>' | node "$HOME/.claude/skills/ck/commands/save.mjs" --init

Confirmed JSON schema: {"name":"...","path":"...","description":"...","stack":["..."],"goal":"...","constraints":["..."],"repo":"..." }


/ck:save — Save Session State

This is the only command requiring LLM analysis. Analyze the current conversation:

  • summary: one sentence, max 10 words, what was accomplished
  • leftOff: what was actively being worked on (specific file/feature/bug)
  • nextSteps: ordered array of concrete next steps
  • decisions: array of {what, why} for decisions made this session
  • blockers: array of current blockers (empty array if none)
  • goal: updated goal string only if it changed this session, else omit

Show a draft summary to the user: "Session: '<summary>' — save this? (yes / edit)" Wait for confirmation. Then pipe to save.mjs:

echo '<json>' | node "$HOME/.claude/skills/ck/commands/save.mjs"

JSON schema (exact): {"summary":"...","leftOff":"...","nextSteps":["..."],"decisions":[{"what":"...","why":"..."}],"blockers":["..."]} Display the script's stdout confirmation verbatim.


/ck:resume [name|number] — Full Briefing

node "$HOME/.claude/skills/ck/commands/resume.mjs" [arg]

Display output verbatim. Then ask: "Continue from here? Or has anything changed?" If user reports changes → run /ck:save immediately.


/ck:info [name|number] — Quick Snapshot

node "$HOME/.claude/skills/ck/commands/info.mjs" [arg]

Display output verbatim. No follow-up question.


/ck:list — Portfolio View

node "$HOME/.claude/skills/ck/commands/list.mjs"

Display output verbatim. If user replies with a number or name → run /ck:resume.


/ck:forget [name|number] — Remove a Project

First resolve the project name (run /ck:list if needed). Ask: "This will permanently delete context for '<name>'. Are you sure? (yes/no)" If yes:

node "$HOME/.claude/skills/ck/commands/forget.mjs" [name]

Display confirmation verbatim.


/ck:migrate — Convert v1 Data to v2

node "$HOME/.claude/skills/ck/commands/migrate.mjs"

For a dry run first:

node "$HOME/.claude/skills/ck/commands/migrate.mjs" --dry-run

Display output verbatim. Migrates all v1 CONTEXT.md + meta.json files to v2 context.json. Originals are backed up as meta.json.v1-backup — nothing is deleted.


SessionStart Hook

The hook at ~/.claude/skills/ck/hooks/session-start.mjs must be registered in ~/.claude/settings.json to auto-load project context on session start:

{
  "hooks": {
    "SessionStart": [
      { "hooks": [{ "type": "command", "command": "node \"~/.claude/skills/ck/hooks/session-start.mjs\"" }] }
    ]
  }
}

The hook injects ~100 tokens per session (compact 5-line summary). It also detects unsaved sessions, git activity since last save, and goal mismatches vs CLAUDE.md.


Rules

  • Always expand ~ as $HOME in Bash calls.
  • Commands are case-insensitive: /CK:SAVE, /ck:save, /Ck:Save all work.
  • If a script exits with code 1, display its stdout as an error message.
  • Never edit context.json or CONTEXT.md directly — always use the scripts.
  • If projects.json is malformed, tell the user and offer to reset it to {}.