PluginBench
Skill
Pass
Audit score 90

ck

affaan-m/everything-claude-code

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

What is ck?

Context Keeper maintains structured project memory across 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-load project context on session start via SessionStart hook
  • Save session summaries, decisions, blockers, and next steps to persistent JSON
  • Resume full briefings or quick snapshots of any tracked project
  • Track git activity and detect unsaved sessions since last save
  • Run deterministic Node.js scripts for consistent behavior across model versions
  • Migrate legacy v1 context data to v2 structured format

How to install ck

npx skills add https://github.com/affaan-m/everything-claude-code --skill ck
Prerequisites
  • Node.js installed
  • SessionStart hook registered in ~/.claude/settings.json (optional but recommended for auto-load)
Claude Code
Cursor
Windsurf
Cline

How to use ck

  1. 1.Run `/ck:init` to register a new project and confirm auto-detected metadata
  2. 2.Work on your project normally
  3. 3.Run `/ck:save` at the end of a session to capture summary, decisions, blockers, and next steps
  4. 4.Run `/ck:resume [name]` at the start of a new session to load full context
  5. 5.Use `/ck:list` to view all tracked projects and `/ck:info [name]` for quick snapshots
  6. 6.Run `/ck:forget [name]` to remove a project from tracking

Use cases

Good for
  • Resume a multi-session project without re-explaining the entire codebase
  • Track architectural decisions and constraints across team members or time
  • Detect when you've made progress but haven't saved context, prompting a save
  • Maintain a portfolio of active projects and switch between them quickly
  • Preserve blockers and next steps so context isn't lost between sessions
Who it's for
  • Claude Code users managing multiple projects
  • Teams needing persistent project memory across sessions
  • Developers working on long-running features or refactors
  • Anyone wanting deterministic, model-agnostic session state

ck FAQ

Do I need to manually edit context.json or CONTEXT.md?

No. Never edit them directly — always use the `/ck:*` commands. The scripts handle all updates.

What happens if I don't run the SessionStart hook?

Context won't auto-load on session start, but you can still manually run `/ck:resume` to load it. The hook is optional but recommended.

Can I migrate from v1 to v2?

Yes. Run `/ck:migrate --dry-run` first to preview changes, then `/ck:migrate` to convert. Original v1 files are backed up.

How much context does the SessionStart hook inject?

Approximately 100 tokens per session — a compact 5-line summary designed to be lightweight while preserving essential state.

What if projects.json becomes corrupted?

The skill will alert you and offer to reset it to an empty object `{}`. You can then re-register projects with `/ck:init`.

Full instructions (SKILL.md)

Source of truth, from affaan-m/everything-claude-code.


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 {}.