Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
Prunes a bloated Claude Code session with the cozempic CLI using a gentle, standard or aggressive prescription, after a dry run and your confirmation.
Install Cozempic Session Pruning
$ npx skills add Ruya-AI/cozempic --skill treat -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Ruya-AI/cozempic treat --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Ruya-AI/cozempic.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugin/skills/treat .claude/skills/treat && rm -rf skills-srcUse ~/.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/
Install the "treat" agent skill from https://github.com/Ruya-AI/cozempic/tree/main/plugin/skills/treat into .claude/skills/treat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "treat", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Ruya-AI/cozempic/tree/main/plugin/skills/treatType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Ruya-AI/cozempic --skill treat -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Ruya-AI/cozempic treat --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Ruya-AI/cozempic.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugin/skills/treat .agents/skills/treat && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "treat" agent skill from https://github.com/Ruya-AI/cozempic/tree/main/plugin/skills/treat into .agents/skills/treat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "treat", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Ruya-AI/cozempic --skill treat -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Ruya-AI/cozempic treat --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Ruya-AI/cozempic.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugin/skills/treat .cursor/skills/treat && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "treat" agent skill from https://github.com/Ruya-AI/cozempic/tree/main/plugin/skills/treat into .cursor/skills/treat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "treat", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Ruya-AI/cozempic.git --path plugin/skills/treat--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Ruya-AI/cozempic --skill treat -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Ruya-AI/cozempic treat --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Ruya-AI/cozempic.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugin/skills/treat .gemini/skills/treat && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "treat" agent skill from https://github.com/Ruya-AI/cozempic/tree/main/plugin/skills/treat into .gemini/skills/treat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "treat", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Ruya-AI/cozempic treatInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Ruya-AI/cozempic --skill treat -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Ruya-AI/cozempic.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugin/skills/treat .github/skills/treat && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "treat" agent skill from https://github.com/Ruya-AI/cozempic/tree/main/plugin/skills/treat into .github/skills/treat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "treat", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Ruya-AI/cozempic --skill treat -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Ruya-AI/cozempic treat --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Ruya-AI/cozempic.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugin/skills/treat .opencode/skills/treat && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "treat" agent skill from https://github.com/Ruya-AI/cozempic/tree/main/plugin/skills/treat into .opencode/skills/treat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "treat", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
treat- GitHub stars
- 425
- Token cost
- ~546 tokens
- SKILL.md length
- 214 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 using a gentle, standard or aggressive prescription, after a dry run and your confirmation.
- Works in 6 steps: Diagnose first — show the user what… → Dry-run the treatment — show savings… → Show results — present the dry-run… → …
- Shrinking a long session that has filled up with tool output
- SKILL.md covers Steps, Prescriptions and Safety
- Calls claude
What it does
The agent first diagnoses the current session, then runs the chosen prescription as a dry run and shows the savings in both bytes and tokens. Only after you confirm does it re-run with --execute. Standard is the default when no prescription is named.
Prescriptions stack. Gentle collapses progress ticks, dedupes file history and strips metadata; standard adds thinking blocks, tool output trimming, stale reads and system-reminder dedup; aggressive adds error-retry collapse, document dedup, mega-block trim and envelope strip. A timestamped backup is made automatically and conversation parent links stay intact. The companion reload skill does the same prune with automatic resume, so this one is for staying in the current session, after which you resume with claude --resume.
When your agent uses it
- Shrinking a long session that has filled up with tool output
- Previewing how many tokens a prune would save before applying it
- Pruning without leaving the current session or terminal
Example prompts
- “Prune this session with the aggressive prescription, but show me a dry run first.”
- “Diagnose how bloated this conversation is.”
- “Treat the session with the standard prescription and tell me the token savings.”
Requirements
- The cozempic CLI
- Pre-approved tools (allowed-tools): Bash(cozempic *), AskUserQuestion
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Diagnose first — show the user what they're working with
- Dry-run the treatment — show savings without applying
- Show results — present the dry-run output including token savings (the Tokens: line). Always surface both byte and token savings.
- Ask confirmation — use AskUserQuestion to confirm before applying.
- Apply on confirmation
- Tell the user: "Treatment applied. A backup was created automatically. To resume with the pruned session, exit and run claude --resume…
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
Shell commands in SKILL.md call:
claude
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
Cozempic Session Pruning loads about 546 tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 214 words of instructions outside code blocks.
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). 214 words, ~546 tokens.
Download SKILL.mdSave it as
.claude/skills/treat/SKILL.md (or your agent's skills folder).- name
- treat
- description
- Prune bloated session with a prescription. Removes progress ticks, stale reads, duplicate content, and more.
- allowed-tools
- Bash(cozempic *), AskUserQuestion
- argument-hint
- [gentle|standard|aggressive]
- disable-model-invocation
- true
Apply a pruning prescription to the current session. Default is standard if no argument given.
When to use treat vs reload: prefer the reload skill — it does the same prune plus auto-resume in one step (/exit → new terminal opens with the pruned session). Use treat only when the user explicitly wants to stay in the current session, work in a multi-pane setup, or resume manually.
Steps
Diagnose first — show the user what they're working with:
bash cozempic current --diagnoseDry-run the treatment — show savings without applying:
bash cozempic treat current -rx $ARGUMENTSIf no argument was provided, use
standard:bash cozempic treat current -rx standardShow results — present the dry-run output including token savings (the
Tokens:line). Always surface both byte and token savings.Ask confirmation — use AskUserQuestion to confirm before applying.
Apply on confirmation:
bash cozempic treat current -rx $ARGUMENTS --executeTell the user: "Treatment applied. A backup was created automatically. To resume with the pruned session, exit and run
claude --resume. (Tip: next time, thereloadskill does this in one step —/exitand a fresh terminal opens automatically.)"
Prescriptions
| Rx | Strategies | Typical Savings |
|---|---|---|
gentle | progress-collapse, file-history-dedup, metadata-strip | 40-55% |
standard | gentle + thinking-blocks, tool-output-trim, stale-reads, system-reminder-dedup | 50-70% |
aggressive | standard + error-retry-collapse, document-dedup, mega-block-trim, envelope-strip | 70-95% |
Safety
- Always dry-run first — never execute without showing the user what will change
- Backups are automatic (timestamped .bak files)
- Never touches uuid/parentUuid — conversation DAG stays intact
© 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/treat of Ruya-AI/cozempic.
Open the folder on GitHubat commit fd41e95
Compare with similar skills
Cozempic Session Pruning 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cozempic Session Pruning this skillRuya-AI/cozempic | 425 | — | ~546 | Automated safety check: Pass | MIT | |
| Context Mode Output Sandboxmksglu/context-mode | 26k | — | ~4.1k | Automated safety check: Pass | Custom licence | |
| Memori Long-Term MemoryMemoriLabs/Memori | 17k | — | ~2k | Automated safety check: Notes | Custom licence | |
| Picoclaw Skill Creatorsipeed/picoclaw | 30k | — | ~4.4k | Automated safety check: Pass | MIT | |
| Context Mode for Antigravity CLImksglu/context-mode | 26k | — | ~850 | Automated safety check: Pass | Custom licence | |
| ccc Semantic Code Searchcocoindex-io/cocoindex-code | 2.8k | — | ~938 | Automated safety check: Pass | Apache-2.0 |
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.
Picoclaw Skill Creator
sipeed/picoclaw
Guidance for creating, updating and reviewing Picoclaw skills, from the SKILL.md structure to organizing bundled scripts, references and assets.
Context Mode for Antigravity CLI
mksglu/context-mode
Routing rules for using context-mode MCP tools in Antigravity CLI: sandboxed code runs, file analysis, indexed search and web fetches that keep large output out of the conversation.
ccc Semantic Code Search
cocoindex-io/cocoindex-code
Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path.
Token Optimizer
alexgreensh/token-optimizer
Audits a Claude Code or Codex setup for context-window waste, fixes it with the user's approval, and measures the saving.
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.
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.
Diagnose
Ruya-AI/cozempic
Analyze Claude Code session bloat — shows token count, context usage %, and bloat breakdown.
Session Reload and Prune
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.
Related
Categories
Questions about Cozempic Session Pruning
What does Cozempic Session Pruning do?
Prunes a bloated Claude Code session with the cozempic CLI using a gentle, standard or aggressive prescription, after a dry run and your confirmation. The agent first diagnoses the current session, then runs the chosen prescription as a dry run and shows the savings in both bytes and tokens. Only after you confirm does it re-run with --execute.
When should I use Cozempic Session Pruning?
Cozempic Session Pruning fits situations like: shrinking a long session that has filled up with tool output; previewing how many tokens a prune would save before applying it; pruning without leaving the current session or terminal.
How do I install Cozempic Session Pruning in Claude Code?
Run `npx skills add Ruya-AI/cozempic --skill treat -a claude-code`. Or copy the skill folder (plugin/skills/treat in Ruya-AI/cozempic) into .claude/skills/treat in your project. Claude Code loads it when a task matches its description.
How do I install Cozempic Session Pruning in Codex?
Run `npx skills add Ruya-AI/cozempic --skill treat -a codex`. Or copy the skill folder (plugin/skills/treat in Ruya-AI/cozempic) into .agents/skills/treat in your project. Codex loads it when a task matches its description.
Can I use Cozempic Session Pruning 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 treat -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/treat, .gemini/skills/treat, .github/skills/treat and .opencode/skills/treat in your project.
What does Cozempic Session Pruning need to run?
Going by SKILL.md and its folder, Cozempic Session Pruning needs the command-line tools its instructions call (claude). Our summary lists: The cozempic CLI. Its frontmatter pre-approves these tools: Bash(cozempic *), AskUserQuestion.
Does Cozempic Session Pruning 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 Cozempic Session Pruning 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 Cozempic Session Pruning use?
Cozempic Session Pruning 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 Cozempic Session Pruning use?
About 546 tokens (SKILL.md is roughly 2.2k 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 Cozempic Session Pruning?
Skills that share tags, products or a category with Cozempic Session Pruning: Context Mode Output Sandbox (mksglu/context-mode, 26k stars), Memori Long-Term Memory (MemoriLabs/Memori, 17k stars), Picoclaw Skill Creator (sipeed/picoclaw, 30k stars) and Context Mode for Antigravity CLI (mksglu/context-mode, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cozempic Session Pruning?
Ruya-AI (a GitHub organization) maintains it in Ruya-AI/cozempic, which has 425 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.