Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Session End

ASecurity

Manages `.claude/session-log.md` — a per-project rolling log of session summaries, one entry per day, last 10 days kept. ``` /session-end → write today's summary (manual, high quality) /session-end show → print the last entry /session-end all → print all entries (oldest → newest) ``` ---

42 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgobashgit

Works with

claude code

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add valpere/session-indexer --skill session-end --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Session End?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Session End
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/valpere-session-end/badge)](https://www.skillsdirectory.com/skills/valpere-session-end)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
# /session-end

Manages `.claude/session-log.md` — a per-project rolling log of session
summaries, one entry per day, last 10 days kept.

```
/session-end          → write today's summary (manual, high quality)
/session-end show     → print the last entry
/session-end all      → print all entries (oldest → newest)
```

---

## /session-end (no args) — write today's summary

Review the current conversation and write today's entry to
`.claude/session-log.md`. Use this before switching projects or closing
Claude Code. The Stop hook (if configured) auto-generates a summary on
exit, but `/session-end` produces better output — full session context,
not transcript extraction.

If an entry for today already exists it is **replaced**, not duplicated.
After write, the log is rotated to keep the last 10 day-entries.

### Entry format

```markdown
## YYYY-MM-DD

### Що зробили
- completed item

### Поточний стан
- current branch / open PR number
- what is working / what is broken

### Відкриті питання
- unresolved question (omit section if none)

### Наступні кроки
- next item, in priority order
```

Rules: 10–20 bullets total · Ukrainian for content · English for code/files/identifiers · include PR number and branch in Поточний стан · omit Відкриті питання if none.

### Write logic

Build the entry text (starting with `## YYYY-MM-DD`, following the format
above), then call the shared rotation helper — same one used by the
`session-end.sh` Stop hook, so both paths behave identically:

```bash
source .claude/hooks/_lib/hook-common.sh

ENTRY="## $(date '+%Y-%m-%d')

### Що зробили
- ...

### Поточний стан
- ...

### Наступні кроки
- ..."

hook_rotate_log .claude/session-log.md "$ENTRY"
```

After writing, report:
> "Session log updated — `.claude/session-log.md`, entry for {today}."

---

## /session-end show — print last entry

```bash
source .claude/hooks/_lib/hook-common.sh

if [[ ! -f .claude/session-log.md ]]; then
  echo 'No session log found. Run `/session-end` to create one.'
else
  hook_read_log_entries .claude/session-log.md
  if (( ${#LOG_ENTRIES[@]} > 0 )); then
    printf '%s\n' "${LOG_ENTRIES[-1]}"
  else
    echo '(no entries)'
  fi
fi
```

---

## /session-end all — print all entries

```bash
source .claude/hooks/_lib/hook-common.sh

if [[ ! -f .claude/session-log.md ]]; then
  echo 'No session log found.'
else
  hook_read_log_entries .claude/session-log.md
  for entry in "${LOG_ENTRIES[@]}"; do
    printf '%s\n\n' "$entry"
  done
  if (( ${#LOG_ENTRIES[@]} > 0 )); then
    first_date=$(head -1 <<< "${LOG_ENTRIES[0]}" | sed 's/^## //')
    last_date=$(head -1 <<< "${LOG_ENTRIES[-1]}" | sed 's/^## //')
    echo "${#LOG_ENTRIES[@]} entries: $first_date → $last_date"
  fi
fi
```

---

## How the full system works

```
Session ends (exit / /exit)
  └─ Stop hook: .claude/hooks/session-end.sh   (configured ✓)
       ├─ Skip if /session-end ran within 2h (file mtime check)
       ├─ Try agy -p  — Gemini 3.5 Flash (Low → Medium → High), Gemini 3.1 Pro (Low → High)
       ├─ Try opencode run --format json  — ollama/glm-5.2:cloud, kimi-k2.7-code:cloud,
       │                                    minimax-m3:cloud, qwen3.5:cloud
       └─ Fallback: raw transcript excerpt

Next session opens
  └─ SessionStart hook: .claude/hooks/session-last.sh   (configured ✓)
       ├─ Reads last ## YYYY-MM-DD entry from session-log.md
       ├─ Skips if entry is >30 days old
       └─ Injects as additionalContext: "Previous session context (Xd Yh ago): ..."
```

LLM fallback chain (Stop hook):
1. `agy` — Gemini 3.5 Flash (cheapest first), Gemini 3.1 Pro
2. `opencode` — glm-5.2:cloud, kimi-k2.7-code:cloud, minimax-m3:cloud, qwen3.5:cloud
3. Raw transcript excerpt (fallback)

The skill works standalone (without hooks) — you just run `/session-end`
manually. The hooks add automation.

**Log file**: `.claude/session-log.md` (gitignored ✓)

**Troubleshooting** (if hooks misbehave):
```bash
tail -30 ~/.cache/session-indexer/hooks.log
cat .claude/session-log.md
```

Attribution

valperevalpere
View sourceMore from valpere →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →