How do I install the Agent Cleaner Skills skill?

Run npx skillmds@latest add legendtkl/agent-cleaner-skills in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Agent Cleaner Skills safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Agent Cleaner Skills?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Agent Cleaner Skills free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Agent Cleaner Skills?

legendtkl (@legendtkl) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Agent Cleaner Skills by legendtkl — Agent Skill

Name: Agent Cleaner Skills
Author: legendtkl

Agent Cleaner Skills

Identify unused Codex skills and MCP servers and disable them to reduce system-prompt context bloat. Use when the user asks to clean up / slim / 瘦身 their Codex skills or MCP servers, audit which are unused, or recover context budget.

legendtkl 3bb2247 3.3 KB Updated Sep 17, 2026

File contents

agent-cleaner — Codex skills and MCP server slimming

When the user wants to slim Codex skills or MCP servers, follow the same flow: enumerate → suggest → confirm → disable. The CLI exposes parallel skills and mcp command trees on Codex (subagents are Claude Code-only).

1. Locate the bundled CLI

Prefer ${AGENT_CLEANER_CLI} if set. Otherwise locate the newest installed bundle:

find "${CODEX_HOME:-$HOME/.codex}/plugins/cache/local/agent-cleaner" -path '*/lib/agent-cleaner.mjs' -type f 2>/dev/null | sort | tail -1

If that finds nothing, check the current repository path:

test -f plugins/codex/lib/agent-cleaner.mjs && pwd

Always invoke via node <abs-path> and always pass --host=codex.

2. Listing and suggesting

node "<abs-path>/agent-cleaner.mjs" --host=codex skills suggest --json

The output is a JSON array of suggestions, each with id, name, source, reason (never-used | stale), confidence (high | medium | low), details.

If the user wants to see all skills, use skills list --json.

3. Confirm with the user

Show the suggestion list as a compact table with id, reason, and confidence. Never disable without explicit user confirmation.

If the user wants to adjust the staleness threshold, mention --unused-for=60d (or 2w, 3m, 1y) or persist a default in ~/.agent-cleaner/config.json:

{ "unusedForDays": 60 }

4. Disable

Either pass specific ids:

node "<abs-path>/agent-cleaner.mjs" --host=codex skills disable user:codex:lark-mail plugin:gmail@openai-curated:gmail --yes

Or apply all current suggestions in one shot:

node "<abs-path>/agent-cleaner.mjs" --host=codex skills disable --all-suggested --yes

After disable succeeds, tell the user: "Disabled N skills. Restart Codex or start a new Codex session for the change to take effect."

5. Other operations

skills enable <id...> — undo a disable.
skills status [--json] — list currently-disabled skills and detect/auto-reapply any that an upstream plugin or skill update may have restored.
skills list --json — full inventory with lastUsed and callCount.

6. MCP servers

The same verbs apply with mcp instead of skills. Codex MCP servers live as [mcp_servers.NAME] blocks in ~/.codex/config.toml:

node "<abs-path>/agent-cleaner.mjs" --host=codex mcp suggest --json
node "<abs-path>/agent-cleaner.mjs" --host=codex mcp disable mcp:user:codex:linear --yes
node "<abs-path>/agent-cleaner.mjs" --host=codex mcp disable --all-suggested --yes

Usage is detected from mcp__<server>__<tool> tool calls in Codex session transcripts under ~/.codex/sessions/.

Constraints

Codex system skills under ~/.codex/skills/.system cannot be disabled.
Skills disable: mv SKILL.md SKILL.md.agent-cleaner-disabled. MCP disable: the [mcp_servers.NAME] block is spliced out of config.toml and the original lines are stashed in state. enable reverses both.
State is kept at ~/.agent-cleaner/state-codex.json.

---name: agent-cleaner-skillsdescription: Identify unused Codex skills and MCP servers and disable them to reduce system-prompt context bloat. Use when the user asks to clean up / slim / 瘦身 their Codex skills or MCP servers, audit which are unused, or recover context budget.---# agent-cleaner — Codex skills and MCP server slimmingWhen the user wants to slim Codex skills or MCP servers, follow the sameflow: enumerate → suggest → confirm → disable. The CLI exposes parallel`skills` and `mcp` command trees on Codex (subagents are Claude Code-only).## 1. Locate the bundled CLIPrefer `${AGENT_CLEANER_CLI}` if set. Otherwise locate the newest installed bundle:```bashfind "${CODEX_HOME:-$HOME/.codex}/plugins/cache/local/agent-cleaner" -path '*/lib/agent-cleaner.mjs' -type f 2>/dev/null | sort | tail -1```If that finds nothing, check the current repository path:```bashtest -f plugins/codex/lib/agent-cleaner.mjs && pwd```Always invoke via `node <abs-path>` and always pass `--host=codex`.## 2. Listing and suggesting```bashnode "<abs-path>/agent-cleaner.mjs" --host=codex skills suggest --json```The output is a JSON array of suggestions, each with `id`, `name`, `source`, `reason` (`never-used` | `stale`), `confidence` (`high` | `medium` | `low`), `details`.If the user wants to see all skills, use `skills list --json`.## 3. Confirm with the userShow the suggestion list as a compact table with id, reason, and confidence. Never disable without explicit user confirmation.If the user wants to adjust the staleness threshold, mention `--unused-for=60d` (or `2w`, `3m`, `1y`) or persist a default in `~/.agent-cleaner/config.json`:```json{ "unusedForDays": 60 }```## 4. DisableEither pass specific ids:```bashnode "<abs-path>/agent-cleaner.mjs" --host=codex skills disable user:codex:lark-mail plugin:gmail@openai-curated:gmail --yes```Or apply all current suggestions in one shot:```bashnode "<abs-path>/agent-cleaner.mjs" --host=codex skills disable --all-suggested --yes```After disable succeeds, tell the user: "Disabled N skills. Restart Codex or start a new Codex session for the change to take effect."## 5. Other operations- `skills enable <id...>` — undo a disable.- `skills status [--json]` — list currently-disabled skills and detect/auto-reapply any that an upstream plugin or skill update may have restored.- `skills list --json` — full inventory with `lastUsed` and `callCount`.## 6. MCP serversThe same verbs apply with `mcp` instead of `skills`. Codex MCP servers live as`[mcp_servers.NAME]` blocks in `~/.codex/config.toml`:```bashnode "<abs-path>/agent-cleaner.mjs" --host=codex mcp suggest --jsonnode "<abs-path>/agent-cleaner.mjs" --host=codex mcp disable mcp:user:codex:linear --yesnode "<abs-path>/agent-cleaner.mjs" --host=codex mcp disable --all-suggested --yes```Usage is detected from `mcp__<server>__<tool>` tool calls in Codex sessiontranscripts under `~/.codex/sessions/`.## Constraints- Codex system skills under `~/.codex/skills/.system` cannot be disabled.- Skills disable: `mv SKILL.md SKILL.md.agent-cleaner-disabled`. MCP disable: the `[mcp_servers.NAME]` block is spliced out of `config.toml` and the original lines are stashed in state. `enable` reverses both.- State is kept at `~/.agent-cleaner/state-codex.json`.

Frequently asked questions