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.
/plugin marketplace add sdsrss/claude-mem-lite/plugin install claude-mem-liteWrote 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.
[](https://agentmods.dev/commands/sdsrss/claude-mem-lite/unadopt)<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="Measured on agentmods" height="20"></a>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 | $0.00086 | $0.00549 |
| Opus 5 | $0.00043 | $0.00275 |
| Sonnet 5 | $0.00017 | $0.00110 |
| Haiku 4.5 | $0.00009 | $0.00055 |
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 8d 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.
What it actually says
/unadopt
Remove the claude-mem-lite steering block from the current project. Opposite of
/adopt.
What it removes
- The
<!-- claude-mem-lite:begin vN --> … <!-- claude-mem-lite:end -->managed block from<cwd>/CLAUDE.md. Everything else in the file is preserved byte-for-byte. <cwd>/.claude/plugin_claude_mem_lite.mddetail doc.<cwd>/.claude/.plugin_claude_mem_lite_state.jsonsidecar (and an emptied.claude/dir).
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 from every project in Claude Code's known-project list (~/.claude.jsonprojects), 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 —cdinto it and run/unadoptthere. Pair with--dry-runto preview.--status— read-only adoption probe (mirrors/adopt --status)
Note: this does not stop auto-adopt
/unadopt removes the block now, but the next SessionStart re-adopts unless you
also disable it: claude-mem-lite adopt --disable (per-project) or
MEM_NO_AUTO_ADOPT=1 (global).
Aftermath
Once unadopted, the conservative hook layer (SessionStart File Lessons /
Key Context, MCP instructions WHEN TO USE) returns to verbose mode on the
next session start.
!node ${CLAUDE_PLUGIN_ROOT}/cli.mjs unadopt $ARGUMENTS
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.
- 8d ago First seen · 47 lines · 86 tokens per session scan A 9f9a0c2f3f2d
unadopt is a command published in the GitHub repository sdsrss/claude-mem-lite (58 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 549 once invoked, about $0.0004 per session on Opus 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.
Other commands, from other repositories
session-save
Save the current session state — decisions, modified files, current status, and next steps — to a handoff file for later resume.
dashboard
Visual dashboard showing instinct health, observation stats, and learning progress.
drift-detect
Configuration drift detection command. Finds inconsistencies, orphaned components, and stale content in the Badi system.
wrap-up
End-of-day ritual command. Prepares the day for closure and sets the stage for tomorrow.
distill
Distill repeated successful tool sequences from the observation log into reusable draft instincts, with an explicit propose-edit-promote ladder. Enforces Law 7 (Learn From Every Session).
recall
Search past tool-call observations with BM25 ranking to answer "have I seen this before?" before re-deriving a fix or repeating a mistake. Enforces Law 1 (Research Before Executing).