Menu
Use when the user says 'save diary', 'log session', 'wrapping up', or at end of a productive session.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Use when the user says 'git-guard', 'check git protection', 'is this repo protected', 'verify gitleaks', 'set up git hooks', 'install git-guard', or wants to confirm a repo blocks secrets and internal files before commit. This is an installer and verifier, NOT a scanner (gitleaks does the actual scanning). Do NOT use for deep secret audits or RLS work.
Use when the user says 'tokenstack', 'compression', 'token savings', 'proxy status', or asks about context window usage.
Use when the user says 'token optimization', 'save tokens', 'context window', 'reduce tokens', 'token stack', or 'TokenStack', or asks about extending context window capacity. Covers TokenStack, the built-in compression proxy that shrinks Claude Code tool output before it reaches the Anthropic API. Do NOT use for proxy troubleshooting or live status (Compress skill).
Use when the user references past sessions, asks 'what did we do', 'do you remember', 'last session', 'recall', or 'continue from'.
Use this skill when the user says 'Hetzner', 'VPS setup', 'server provisioning', 'deploy to VPS', 'hetzner-setup', 'cloud server', or needs to provision, harden, and deploy applications to a Hetzner Cloud server with Docker, Nginx/Caddy, SSL, and monitoring. Do NOT use for managed platform deployments like Railway or Netlify.
Use this skill when the user says 'audit API', 'check API security', 'API routes security', 'endpoint audit', 'check my routes', or needs to verify API route protection. Reviews API endpoints for authentication, authorization, and input validation gaps. Do NOT use for frontend security headers or dependency scanning.
| name | diary |
| description | Use when the user says 'save diary', 'log session', 'wrapping up', or at end of a productive session. |
| version | 1.0.0 |
Document what was accomplished in each CC session for future recall.
When this skill activates, output:
📓 Diary — Logging session...
Then execute the protocol below.
| Context | Status | Priority |
|---|---|---|
| User says "save diary", "log session", "write diary" | ACTIVE — write diary | P1 |
| User explicitly says they're done ("that's it", "wrapping up") | ACTIVE — suggest diary if work was done | P2 |
| Multi-agent session (Builder/Reviewer role) | DORMANT — Manager handles diary | — |
| Mid-session, user is actively coding | DORMANT — don't interrupt flow | — |
| Casual conversation, no code changes made | DORMANT — nothing to log | — |
| User asks to recall past sessions ("what did we do") | DORMANT — Echo handles recall, not Diary | — |
| User says "save project" or "handoff" | DORMANT — Project skill handles this | — |
| Session just started, no work yet | DORMANT — nothing to log | — |
When the user asks to save a diary, keep these in mind:
| Temptation | Why it matters |
|---|---|
| "Nothing important happened" | Even small decisions have context worth capturing. |
| "Commits capture everything" | Commits don't capture decisions, blockers, or next steps. |
| "Skip the handoff section" | Handoffs are the most valuable part for session continuity. |
Always use Bash for all memstack-db.py commands. Do not use PowerShell or CMD -- PowerShell mangles JSON arguments.
All JSON field values must be plain strings. Never pass arrays or objects. If multiple items (files, commits, decisions), join them as a comma-separated string.
Summarize the session:
Check git log for commits:
git log --oneline -10
Format the diary entry:
# Session Diary — {project} — {date}
## Accomplished
- Item 1...
## Files Changed
- path/to/file.ts — description
## Commits
- abc1234 Message
## Decisions
- Decision: reason
## Next Steps
- What to do next
## Session Handoff
**In Progress:** [what was actively being worked on when session ended]
**Uncommitted Changes:** [list any unstaged/uncommitted work, or "None"]
**Pick Up Here:** [exact instruction for next session — specific enough to start cold]
**Session Context:** [anything important that isn't captured elsewhere — temp decisions, debugging state, gotchas discovered]
Save to SQLite database (primary storage):
python "$MEMSTACK_PATH/db/memstack-db.py" add-session '{"project":"<name>","date":"<YYYY-MM-DD>","accomplished":"<bullets>","files_changed":"<bullets>","commits":"<bullets>","decisions":"<bullets>","problems":"<bullets>","next_steps":"<bullets>","duration":"<estimate>","raw_markdown":"<full text>"}'
Also save decisions as insights for cross-project search:
python "$MEMSTACK_PATH/db/memstack-db.py" add-insight '{"project":"<name>","type":"decision","content":"<decision>","context":"Session <date>","tags":"<project>"}'
CRITICAL: The field name is "content", NOT "insight". Using "insight" will fail with a missing required field error.
Update project context with last session date:
python "$MEMSTACK_PATH/db/memstack-db.py" set-context '{"project":"<name>","last_session_date":"<YYYY-MM-DD>"}'
Also save markdown copy to memory/sessions/{date}-{project}.md (export format, human-readable backup)
The 500-line limit on markdown files is no longer a concern since SQLite is the source of truth.
Markdown files in memory/sessions/ are now just human-readable exports.
Old markdown files are preserved but not the primary storage.
User: "save diary"
📓 Diary — Logging session...
Saved: memory/sessions/2026-02-18-adminstack.md
Project: AdminStack | Duration: ~2 hours
Accomplished: Built CC Monitor page, API routes, setup guide
Commits: 4 (45b4c42, d1c7e11, f6c8e18, f0e793f)
Files changed: 8
This session is now searchable via Echo.
The diary system includes an automatic PreCompact hook that fires before Claude Code compresses the context window. This closes the gap where session context could be lost during long conversations.
.claude/diary/{date}-compaction.md — one file per day, appends on multiple compactionsCOMPACTION_INTERRUPTED so the next session knows context was cut| Data | Source |
|---|---|
| Uncommitted changes | git status --short |
| Recent commits | git log --oneline -5 |
| Recent shell commands | Shell history (last 5) |
| Recently modified files | Files modified since last git operation |
| Branch and project | Git branch + directory name |
| Manual Diary | PreCompact Diary | |
|---|---|---|
| Trigger | User says "save diary" | Automatic before compaction |
| Content | Full narrative with decisions, handoff | Snapshot of working state |
| Storage | SQLite + memory/sessions/ | .claude/diary/ only |
| Purpose | Session documentation | Context recovery after compaction |
When resuming after compaction, check .claude/diary/ for entries with today's date. The COMPACTION_INTERRUPTED flag signals that the previous context was truncated and these files contain the lost state.
Hook is registered in .claude/settings.json under PreCompact. Script lives at .claude/hooks/pre-compact.sh. Always exits 0 — must never block compaction.
The Diary skill is part of a broader hook system that automates session lifecycle, security, and observability. All hooks follow the same defensive pattern: set -uo pipefail, SCRIPT_DIR resolution, all external commands wrapped with fallbacks, guaranteed exit 0.
| Event | Script | Matcher | Timeout | Purpose |
|---|---|---|---|---|
| PreToolUse | pre-tool-notify.sh | Write|Edit|MultiEdit|Bash | 10s | TTS voice alert before approval prompts |
| PreToolUse | pre-push.sh | Bash (git push) | 60s | Build verification + secrets scan before push |
| PostToolUse | post-commit.sh | Bash (git commit) | 10s | Debug artifact + secrets scan after commit |
| PostToolUse | post-tool-monitor.sh | Write|Edit|MultiEdit|Bash | 10s | Observation capture — logs tool calls to .claude/observations/ |
| SessionStart | session-start.sh | (all) | 10s | CLAUDE.md indexing, monitoring ping |
| SessionStart | session-context-load.sh | (all) | 15s | Context injection — last 3 diary + observation summaries → .claude/session-context.md |
| Stop | session-end.sh | (all) | 10s | Monitoring API session-complete ping |
| PreCompact | pre-compact.sh | (all) | 15s | Auto-save diary snapshot before context compaction |
settings.json, giving it its own timeout budget.claude/observations/YYYY-MM-DD.md — daily files, append-only.claude/session-context.md on each new session.claude/observations/ and .claude/session-context.md are in .gitignore (ephemeral runtime output).claude/hooks/ and use ${CLAUDE_PROJECT_DIR} for portable path resolution.claude/rules/diary.md), always-on session logging awareness without skill file read. (Origin: MemStack v3.0-beta, Feb 2026)