session-cleanup

session-cleanup is a skill for Claude Code, Codex from apappascs/claude-code-sessions. It costs 50 tokens per session (568 once invoked), scanned A, original, MIT.

A skill that finds old, empty, or very small Claude Code session files that may be removed. It reports each candidate's project, age, message count, and size.

In plain words
What is it for?
Use it to review reclaimable session storage, find sessions older than a chosen age, and delete selected sessions after approval.
Why use it?
It helps identify session data taking up disk space while requiring confirmation before anything is deleted.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the claude-code-sessions plugin — 14 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/apappascs/claude-code-sessions/session-cleanup
Any agent
npx skills add apappascs/claude-code-sessions --skill session-cleanup
Clone the repo
git clone --depth 1 https://github.com/apappascs/claude-code-sessions

Made for: Claude Code, Codex.

Or install claude-code-sessions, the plugin that ships this one along with the rest of its 14 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for session-cleanup

README.md
[![agentmods](https://agentmods.dev/badge/skills/apappascs/claude-code-sessions/session-cleanup.svg)](https://agentmods.dev/skills/apappascs/claude-code-sessions/session-cleanup)
Your own site
<a href="https://agentmods.dev/skills/apappascs/claude-code-sessions/session-cleanup"><img src="https://agentmods.dev/badge/skills/apappascs/claude-code-sessions/session-cleanup.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 568 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.00568
Opus 5 $0.00025 $0.00284
Sonnet 5 $0.00010 $0.00114
Haiku 4.5 $0.00005 $0.00057

Measured 4d ago against content hash e0f18fe79452, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-cleanup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/session-cleanup/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Cleanup

Find session files that are candidates for cleanup.

Step 1: Identify candidates

bun run ${CLAUDE_PLUGIN_ROOT}/lib/session-store.ts cleanup --min-messages 3

To also find old sessions:

bun run ${CLAUDE_PLUGIN_ROOT}/lib/session-store.ts cleanup --older-than 30d --min-messages 3

Step 2: Present candidates

The script outputs a JSON object with candidates array and total_size_bytes. Present as a table:

# Session ID Project Reason Messages Age Size

Show the total reclaimable space.

Step 3: Confirm before deleting

NEVER delete without explicit user confirmation. Present the list and ask:

"Found N sessions (X total) that could be cleaned up. Want me to delete them? (yes/no)"

If confirmed, delete each session using the delete command:

bun run ${CLAUDE_PLUGIN_ROOT}/lib/session-store.ts delete-session <session-id>

This will also report any task lists that become orphaned.

For manual deletion, the file path is also shown:

rm "<path-to-session.jsonl>"

Report each deletion. If the user wants to keep some, ask which ones to skip.

Step 4: Check for orphan task lists

After cleanup, check for task lists that no longer have matching sessions:

bun run ${CLAUDE_PLUGIN_ROOT}/lib/session-store.ts orphan-task-lists

If orphans are found, present them:

Task List ID Tasks Last Modified

Ask: "Found N orphan task lists with no matching session. Delete them? (yes/no/select)"

If confirmed, delete using:

bun run ${CLAUDE_PLUGIN_ROOT}/lib/session-store.ts delete-task-list <task-list-id>

Or the user can inspect and delete manually:

ls ~/.claude/tasks/<task-list-id>/
rm -r ~/.claude/tasks/<task-list-id>/

Safety

  • The script only identifies candidates — it never deletes
  • Always show the full list before asking for confirmation
  • Delete one file at a time, reporting each
  • If in doubt, suggest the user review the list first

Read the full file on GitHub · 85 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 85 lines · 50 tokens per session scan A e0f18fe79452

Subscribe to this mod's changes

session-cleanup is a skill published in the GitHub repository apappascs/claude-code-sessions (4 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 568 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens