ck
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.
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- ck
- repo
- https://github.com/sreedhargs89/context-keeper
- author
- sreedhargs89
- version
- 2.0.0
- metadata
- { "origin": "community" }
- 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.
02 资源文件 9
- 脚本commands/forget.mjs1.3 KB
- 脚本commands/info.mjs650 B
- 脚本commands/init.mjs6.0 KB
- 脚本commands/list.mjs1.1 KB
- 脚本commands/migrate.mjs7.2 KB
- 脚本commands/resume.mjs949 B
- 脚本commands/save.mjs7.4 KB
- 脚本commands/shared.mjs14.9 KB
- 脚本hooks/session-start.mjs8.6 KB
03 SKILL.md 正文
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 "$HOME/.claude/skills/ck/commands/save.mjs" --init
Confirmed JSON schema: {"name":"...","path":"...","description":"...","stack":["..."],"goal":"...","constraints":["..."],"repo":"..." }
/ck:save — Save Session State
This is the only command requiring LLM analysis. Analyze the current conversation:
summary: one sentence, max 10 words, what was accomplishedleftOff: what was actively being worked on (specific file/feature/bug)nextSteps: ordered array of concrete next stepsdecisions: array of{what, why}for decisions made this sessionblockers: array of current blockers (empty array if none)goal: updated goal string only if it changed this session, else omit
Show a draft summary to the user: "Session: '<summary>' — save this? (yes / edit)"
Wait for confirmation. Then pipe to save.mjs:
echo '<json>' | node "$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$HOMEin Bash calls. - Commands are case-insensitive:
/CK:SAVE,/ck:save,/Ck:Saveall work. - If a script exits with code 1, display its stdout as an error message.
- Never edit
context.jsonorCONTEXT.mddirectly — always use the scripts. - If
projects.jsonis malformed, tell the user and offer to reset it to{}.
04 同仓库更多 Skills
rag-architect-agent
Agente Arquiteto de RAG, Embeddings & Busca Vetorial. Especialista em design e implementação de pipelines de Retrieval-Augmented Generation de alta fidelidade: chunking semântico, modelagem pgvector no PostgreSQL (Neon/Supabase), busca híbrida (cosseno + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).
rag-architecture-patterns
Padrões arquiteturais e implementação de pipelines RAG (Retrieval-Augmented Generation) de alta fidelidade para qualquer projeto ou sistema. Cobre chunking semântico, embeddings, busca híbrida (pgvector + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).
skill-repair
Use this to fix and re-install agent skills that have failed installation. This skill provides the necessary context and permissions to surgically update the `manifest.json` after a fix has been applied.
security-scan
Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.
security-review
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
security-bounty-hunter
Hunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify for real reports instead of noisy local-only findings.