Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/sdsrss/claude-mem-lite/adoptgit clone --depth 1 https://github.com/sdsrss/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/adopt)<a href="https://agentmods.dev/commands/sdsrss/claude-mem-lite/adopt"><img src="https://agentmods.dev/badge/commands/sdsrss/claude-mem-lite/adopt.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 | $0.00101 | $0.00955 |
| Opus 5 | $0.00051 | $0.00477 |
| Sonnet 5 | $0.00020 | $0.00191 |
| Haiku 4.5 | $0.00010 | $0.00096 |
Grade A, and why
adopt 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/adopt
Install the claude-mem-lite steering block into the current project's
CLAUDE.md (the canonical home for project instructions — loaded by Claude Code
at system-prompt authority). This replaces the pre-v3.13 scheme that seeded the
project's memory-dir MEMORY.md; that polluted an index meant for the user's own
memories, and MEMORY.md carries no more weight than CLAUDE.md anyway.
This normally runs automatically on every SessionStart — invoke /adopt only to
force it immediately (e.g. after editing the block out by hand).
What it writes
<cwd>/CLAUDE.md— a concise<!-- claude-mem-lite:begin v1 -->…<!-- :end -->managed block (trigger table →mem_recall/mem_save/mem_defer). Slug-scoped: only this block is managed; the rest of yourCLAUDE.mdis preserved verbatim. Auto-refreshes when the shipped content drifts.<cwd>/.claude/plugin_claude_mem_lite.md— the full contract (tool tables, CLI cheatsheet, citation/decay + save discipline). First line is a<!-- managed-by: claude-mem-lite -->marker. Not auto-loaded; the CLAUDE.md block points to it and Claude reads it on demand.<cwd>/.claude/.plugin_claude_mem_lite_state.json— drift-tracking sidecar.
It also migrates this project's legacy memory-dir sentinel away (strips the
claude-mem-lite:* block from MEMORY.md and deletes the old memory-dir detail
doc). Other plugins' blocks (e.g. code-graph-mcp:*) and your own prose survive.
Flags
--force— also force-clean a legacy memory-dir block lacking a state sidecar--dry-run— print intended writes without touching disk--all— legacy-cleanup sweep: strip the old memory-dir sentinel across every project at once. (It does NOT write CLAUDE.md blocks for other projects — their real paths can't be recovered from the encoded memdir slug; those adopt per-project on each one's next SessionStart.)--status— show this project's adoption + count of memdirs awaiting migration--disable/--enable— per-project opt-out of automatic SessionStart adopt
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.
- 5d ago First seen · 68 lines · 101 tokens per session scan A 1d5e8b30d7fb
adopt is a command published in the GitHub repository sdsrss/claude-mem-lite (57 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 955 once invoked, about $0.0005 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.
presence-reset
Wipe presence state for the current project, all projects, or specific subsystems. Asks for confirmation before destructive action.
clear
Context-clearing command. Provides a seamless transition across session boundaries. Target: under 30 seconds.
sc-detail
Throughline の退避済みターン（L2 本文 + L3 ツール入出力）を時刻で復元する.
scope
Search your Claude Code session history (full-text, always fresh).
tl
Throughline の UserPromptSubmit hook が /tl を検出し、バトン（現セッション ID）を保存しました。.