A command that removes claude-mem-lite's managed instructions and related files from a project. It can also preview the changes or remove the managed block from all known Claude Code projects.

Uninstalling claude-mem-lite instructions, checking adoption status, previewing removal, and cleaning legacy files.

It cleans up the add-on's project changes while preserving the rest of the user's instructions and other plugins' blocks.

unadopt — Command for Claude Code by sdsrss/claude-mem-lite

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 sdsrss/claude-mem-lite

Claude Code

/plugin install claude-mem-lite

Made for: Claude Code.

Or install claude-mem-lite, the plugin that ships this one along with the rest of its 8 commands, 7 hooks, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/sdsrss/claude-mem-lite/unadopt/github.svg)](https://agentmods.dev/commands/sdsrss/claude-mem-lite/unadopt)

Your own site

<a href="https://agentmods.dev/commands/sdsrss/claude-mem-lite/unadopt"><img src="https://agentmods.dev/badge/commands/sdsrss/claude-mem-lite/unadopt/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/sdsrss/claude-mem-lite/unadopt"><img src="https://agentmods.dev/badge/commands/sdsrss/claude-mem-lite/unadopt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 118 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 891 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00118	$0.00891
Opus 5.5	$0.00047	$0.00356
Sonnet 5.5	$0.00024	$0.00178
Haiku 4.5	$0.00012	$0.00089

Measured 2d ago against content hash 029d1caecf6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unadopt 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 2d 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.

commands/unadopt.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/unadopt

Remove the claude-mem-lite steering block from the current project. Opposite of /adopt.

What it removes

The  …  managed block from <cwd>/CLAUDE.md. Everything else in the file is preserved byte-for-byte.
<cwd>/.claude/plugin_claude_mem_lite.md detail doc.
<cwd>/.claude/.plugin_claude_mem_lite_state.json sidecar (and an emptied .claude/ dir).
The block auto-adopt keeps in CLAUDE.local.md at the git repository root, or in .claude/rules/claude-mem-lite.md there (with CLAUDE_MEM_RULES_STEERING=1, next to an AGENTS.md; the file too, when nothing else is in it, and an emptied .claude/rules/ and .claude/), and the lines it added to .git/info/exclude. Those lines stay while another worktree of the repository still has the block, or while a file the plugin created still holds your own notes. Nothing is edited through a symbolic link.

It also cleans any leftover legacy memory-dir sentinel + detail doc for this project (slug-scoped — other plugins' blocks survive).

Flags

--force — also remove a legacy memory-dir block lacking a state sidecar
--dry-run — preview what would be removed; no writes
--all — remove the CLAUDE.md managed block and the auto-written local block from every project in Claude Code's known-project list (projects in ~/.claude.json, or $CLAUDE_CONFIG_DIR/.claude.json), plus sweep any legacy memory-dir sentinels. Slug-scoped, so user content and other plugins' blocks survive. A project Claude Code never opened isn't listed — cd into it and run /unadopt there. Pair with --dry-run to preview.
--status — read-only adoption probe (mirrors /adopt --status)

Note: the steering itself continues

/unadopt removes files, not the steering. A local block the plugin created is not written back; the text is added to each session's context instead (node "${CLAUDE_PLUGIN_ROOT}/cli.mjs" adopt --enable lets it write the file again). A project whose CLAUDE.md block you removed gets a local file on the next session, unless the plugin created one there before. Beside an AGENTS.md that CLAUDE.local.md would switch off, no file is written unless CLAUDE_MEM_RULES_STEERING=1. To stop the steering: node "${CLAUDE_PLUGIN_ROOT}/cli.mjs" adopt --disable (per project) or MEM_NO_AUTO_ADOPT=1 (global).

Read the full file on GitHub · 60 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.

2d ago Changed 029d1caecf6d
16d ago Changed · +3 lines · +13 tokens per session d09f6aa5c553
23d ago Changed · +10 lines · +19 tokens per session 22f0e1b83b5f
27d ago Changed 9ce93ad0b727
1mo ago First seen · 47 lines · 86 tokens per session scan A 9f9a0c2f3f2d

Subscribe to this mod's changes

unadopt is a command published in the GitHub repository sdsrss/claude-mem-lite (67 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 891 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.

Claude Code Memory and context fts5 hooks mcp persistence

unadopt

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/unadopt

What it removes

Flags

Note: the steering itself continues

What this file has done since we first saw it

Other commands, from other repositories

session-save

drift-detect

wrap-up

clear

sync

memory-diff