New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Session Reload and Prune

by Ruya-AI in Ruya-AI/cozempic

Prunes a bloated Claude Code session with the cozempic CLI, shows the token savings, and spawns a watcher that reopens the pruned session in a new terminal window.

MITAuto-check passedAgent Workflows

Install Session Reload and Prune

skills CLI
$ npx skills add Ruya-AI/cozempic --skill reload -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Ruya-AI/cozempic reload --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Ruya-AI/cozempic.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugin/skills/reload .claude/skills/reload && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
reload
GitHub stars
423
Token cost
~260 tokens
SKILL.md length
83 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Prunes a bloated Claude Code session with the cozempic CLI, shows the token savings, and spawns a watcher that reopens the pruned session in a new terminal window.

  • Works in 5 steps: Diagnose first → Dry-run → Show results including token savings.… → …
  • A long session has filled up with tool output and slowed down
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • You want a smaller context without losing the conversation

What it does

Diagnosis comes first: the agent runs cozempic against the current session, then a dry run of the treatment at a chosen level, defaulting to standard, and shows the results including token savings. After you confirm, a single reload command prunes the session, saves it and starts a background watcher. Running a separate execute treatment first is ruled out, because reload already treats the session and would prune twice.

When it finishes, the agent tells you to type /exit, and a new Terminal window then opens on its own with the pruned session resumed. The allowed tools are the cozempic command through Bash and the question tool for confirmation. Cozempic is a context-cleaning tool for Claude Code sessions, so this skill suits long conversations that have grown heavy.

When your agent uses it

  • A long session has filled up with tool output and slowed down
  • You want a smaller context without losing the conversation
  • Continuing the same work in a fresh terminal after pruning

Example prompts

  • “Reload this session with the standard pruning level and show me the token savings first.”
  • “My session is bloated; diagnose it and reopen a pruned copy in a new terminal.”

Requirements

  • The cozempic CLI
  • Pre-approved tools (allowed-tools): Bash(cozempic *), AskUserQuestion

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Diagnose first
  2. Dry-run
  3. Show results including token savings. Ask confirmation.
  4. Apply reload (treats + saves + spawns watcher in one shot)
  5. Tell the user: "Treatment applied. Type /exit — a new Terminal window will open automatically with the pruned session."

What it can do on your machine

Read from SKILL.md and the folder at commit fd41e95. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(cozempic *)
    • AskUserQuestion

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Session Reload and Prune loads about 260 tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 83 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~19
When it runs · the whole SKILL.md, loaded when a task matches
~260

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Ruya-AI/cozempic at commit fd41e95, republished under its MIT licence (© Ruya-AI). 83 words, ~260 tokens.

Download SKILL.mdSave it as .claude/skills/reload/SKILL.md (or your agent's skills folder).
name
reload
description
Treat the current session and auto-resume in a new terminal window.
allowed-tools
Bash(cozempic *), AskUserQuestion
argument-hint
[gentle|standard|aggressive]
disable-model-invocation
true

Treat the session and spawn an auto-resume watcher that opens a new terminal after you exit.

Steps

  1. Diagnose first:

    bash
    cozempic current --diagnose

  2. Dry-run:

    bash
    cozempic treat current -rx $ARGUMENTS

    If no argument was provided, use standard:

    bash
    cozempic treat current -rx standard

  3. Show results including token savings. Ask confirmation.

  4. Apply reload (treats + saves + spawns watcher in one shot):

    bash
    cozempic reload -rx $ARGUMENTS

    Do NOT run cozempic treat --execute before cozempic reload — reload already treats internally. Running both would double-treat.

  5. Tell the user: "Treatment applied. Type /exit — a new Terminal window will open automatically with the pruned session."

© Ruya-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugin/skills/reload of Ruya-AI/cozempic.

Open the folder on GitHubat commit fd41e95

Compare with similar skills

Session Reload and Prune next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Session Reload and Prune compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Session Reload and Prune this skillRuya-AI/cozempic423—~260Automated safety check: PassMIT
Memori Long-Term MemoryMemoriLabs/Memori17k—~2kAutomated safety check: NotesCustom licence
Session Handoff Documentthedotmack/claude-mem99k—~1.4kAutomated safety check: PassApache-2.0
Planning with FilesOthmanAdi/planning-with-files27k—~2.9kAutomated safety check: PassMIT
User Thoughts Memorysickn33/agentic-awesome-skills47k1 repos~2.5kAutomated safety check: PassMIT
Planning With FilesOthmanAdi/planning-with-files27k—~3kAutomated safety check: PassMIT

Similar skills

  • Memori Long-Term Memory

    MemoriLabs/Memori

    Connects Claude Code to Memori Cloud for long-term memory, recalling stored context before substantive replies and saving new context afterward.

    17k GitHub stars~2k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check: notes

  • Session Handoff Document

    thedotmack/claude-mem

    Writes a HANDOFF.md capturing goal, state, files, failed attempts and next steps so a fresh agent session can continue exactly where this one stopped.

    99k GitHub stars~1.4k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Planning with Files

    OthmanAdi/planning-with-files

    Keeps a task plan, findings and progress log in markdown files on disk so long agent tasks survive context resets, with Gemini hooks and helper scripts.

    27k GitHub stars~2.9k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

  • User Thoughts Memory

    sickn33/agentic-awesome-skills

    Saves a user's project decisions, rules and preferences into a project-local mdbase so later sessions and other agents can recover the intent.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Agent WorkflowsAuto-check passed

  • Planning With Files

    OthmanAdi/planning-with-files

    Keeps a task plan, findings and progress log as Markdown files in the project so long multi-step agent work survives context resets.

    27k GitHub stars~3k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

  • Harness Engineering

    10xChengTu/harness-engineering

    Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases.

    102 GitHub starsUsed in 1 repo~1k tokens
    Agent WorkflowsAuto-check passed

More from Ruya-AI/cozempic

  • Cozempic Session Guard

    Ruya-AI/cozempic

    Starts a background daemon that watches a Claude Code session's size and prunes it before auto-compaction can discard context or agent-team state.

    423 GitHub stars~434 tokensUpdated 3 mo ago
    Auto-check passed

  • Cozempic Session Pruning

    Ruya-AI/cozempic

    Prunes a bloated Claude Code session with the cozempic CLI using a gentle, standard or aggressive prescription, after a dry run and your confirmation.

    423 GitHub stars~546 tokensUpdated 3 mo ago
    Auto-check passed

  • Cozempic Doctor

    Ruya-AI/cozempic

    Runs cozempic doctor to check Claude Code configuration and sessions for known problems such as trust-dialog hangs, corrupted tool blocks and zombie teams.

    423 GitHub stars~303 tokensUpdated 3 mo ago
    Auto-check passed

  • Diagnose

    Ruya-AI/cozempic

    Analyze Claude Code session bloat — shows token count, context usage %, and bloat breakdown.

    423 GitHub stars~283 tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Session Reload and Prune

What does Session Reload and Prune do?

Prunes a bloated Claude Code session with the cozempic CLI, shows the token savings, and spawns a watcher that reopens the pruned session in a new terminal window. Diagnosis comes first: the agent runs cozempic against the current session, then a dry run of the treatment at a chosen level, defaulting to standard, and shows the results including token savings. After you confirm, a single reload command prunes the session, saves it and starts a background watcher.

When should I use Session Reload and Prune?

Session Reload and Prune fits situations like: A long session has filled up with tool output and slowed down; you want a smaller context without losing the conversation; continuing the same work in a fresh terminal after pruning.

How do I install Session Reload and Prune in Claude Code?

Run `npx skills add Ruya-AI/cozempic --skill reload -a claude-code`. Or copy the skill folder (plugin/skills/reload in Ruya-AI/cozempic) into .claude/skills/reload in your project. Claude Code loads it when a task matches its description.

How do I install Session Reload and Prune in Codex?

Run `npx skills add Ruya-AI/cozempic --skill reload -a codex`. Or copy the skill folder (plugin/skills/reload in Ruya-AI/cozempic) into .agents/skills/reload in your project. Codex loads it when a task matches its description.

Can I use Session Reload and Prune in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Ruya-AI/cozempic --skill reload -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reload, .gemini/skills/reload, .github/skills/reload and .opencode/skills/reload in your project.

What does Session Reload and Prune need to run?

SKILL.md names no scripts, command-line tools or credentials: Session Reload and Prune is instructions for the agent only. Our summary lists: The cozempic CLI. Its frontmatter pre-approves these tools: Bash(cozempic *), AskUserQuestion.

Does Session Reload and Prune access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Session Reload and Prune safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Session Reload and Prune use?

Session Reload and Prune is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Session Reload and Prune use?

About 260 tokens (SKILL.md is roughly 1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Session Reload and Prune?

Skills that share tags, products or a category with Session Reload and Prune: Memori Long-Term Memory (MemoriLabs/Memori, 17k stars), Session Handoff Document (thedotmack/claude-mem, 99k stars), Planning with Files (OthmanAdi/planning-with-files, 27k stars) and User Thoughts Memory (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Session Reload and Prune?

Ruya-AI (a GitHub organization) maintains it in Ruya-AI/cozempic, which has 423 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on July 3, 2026.

Source: Ruya-AI/cozempic on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.