agentmods.dev

uninstall

uninstall is a skill for Claude Code from robinslange/learning-loop. It costs 0 tokens per session (1,218 once invoked), scanned C, original, Apache-2.0.

A guided removal tool for completely uninstalling the learning-loop add-on and its stored indexes.

In plain words
What is it for?
Use it when you want to remove learning-loop, its episodic-memory connection, and its captured indexes. It does not delete anything automatically.
Why use it?
Removing an add-on from its marketplace can leave related settings and captured data behind. This helps identify and remove those leftovers, with confirmation before destructive steps.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the learning-loop plugin — 24 skills, 20 agents, 7 hooks shipped together

not rated 13repo changed 2mo ago C scan 0 tokens original Apache-2.0

Good fit Use it when you want to remove learning-loop, its episodic-memory connection, and its captured indexes. It does not delete anything automatically.

Compare 6 skills from other repositories ↓
View source ↗ robinslange/learning-loop
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add robinslange/learning-loop
Claude Code
/plugin install learning-loop

Made for: Claude Code.

Or install learning-loop, the plugin that ships this one along with the rest of its 24 skills, 20 agents, 7 hooks.

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 uninstall

README.md
[![agentmods](https://agentmods.dev/badge/skills/robinslange/learning-loop/uninstall/github.svg)](https://agentmods.dev/skills/robinslange/learning-loop/uninstall)
Your own site
<a href="https://agentmods.dev/skills/robinslange/learning-loop/uninstall"><img src="https://agentmods.dev/badge/skills/robinslange/learning-loop/uninstall/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for uninstall

Your own site · 80×15
<a href="https://agentmods.dev/skills/robinslange/learning-loop/uninstall"><img src="https://agentmods.dev/badge/skills/robinslange/learning-loop/uninstall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,218 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.01218
Opus 5.5 $0.00000 $0.00487
Sonnet 5.5 $0.00000 $0.00244
Haiku 4.5 $0.00000 $0.00122

Measured 2mo ago against content hash 05413d9e99b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

uninstall scanned grade C with 1 finding 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 2mo 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf <config_dir>/federation/data/peers/
plugin/skills/uninstall/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Uninstall learning-loop

Removing the plugin via /plugin alone leaves three artefacts behind: cached copies of other people's notes under the federation data dir, the episodic-memory MCP entry in ~/.claude.json, and the captured-index data dir. This skill walks the full removal with operator confirmation.

Steps

  1. Confirm intent. Ask the operator to confirm they want to fully remove learning-loop, including all captured indexes (backlinks, justification index, session labels). If they only want hooks off, point them at ${CLAUDE_PLUGIN_ROOT}/README.md — "Disabling parts without uninstalling" covers turning off individual hooks via hooks.disabled and every plugin's hooks via disableAllHooks: true — and stop.

  2. Federation teardown (only if PLUGIN_DATA/federation/config.json or PLUGIN_DATA/vaults.json exists). Do this before removing the plugin: ll-search lives under the plugin data dir, and after step 3 there is nothing left to run.

    Tell the operator plainly what uninstalling does and does not do.

    a. Show them what is live:

    ll-search link list --config-dir <config_dir>

    b. Withdraw the links this machine issued, one per machine listed, and do it while the hub is still reachable:

    ll-search link revoke <key_id> --config-dir <config_dir>

    It tells the hub first and drops the local row second. That order is not arbitrary: this store is this key's only record of what it issued, so dropping the row while the hub still serves the grant leaves nothing to sign a revocation for, and the other machine keeps full authority until the grant expires a year later.

    Only the half this machine signed. A link is two grants. The one the other machine issued to this one is that machine's statement about its own key, and only that machine can withdraw it — link revoke reports when one is still standing, and so should you. Saying "revoked" while half the door is open is worse than saying nothing.

Read the full file on GitHub · 109 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. 2mo ago Changed · +72 lines 05413d9e99b8
  2. 2mo ago Changed · +1 lines 4e715dcba4d6
  3. 2mo ago First seen · 36 lines · 0 tokens per session scan C a655e8690da1

Subscribe to this mod's changes

uninstall is a skill published in the GitHub repository robinslange/learning-loop (13 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,218 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

uninstall compared with skills from other repositories

uninstall next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
uninstallrobinslange/learning-loopSkill134d agoApache-2.0C0Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code