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/toolsgit 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/tools)<a href="https://agentmods.dev/commands/sdsrss/claude-mem-lite/tools"><img src="https://agentmods.dev/badge/commands/sdsrss/claude-mem-lite/tools.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 | $0.00025 | $0.00620 |
| Opus 5 | $0.00013 | $0.00310 |
| Sonnet 5 | $0.00005 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
tools 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 4d 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.
Tool Import
Import skills and agents from GitHub repositories into the resource registry for intelligent dispatch.
Commands
/mem:tools <github-url>— Import all skills/agents from a GitHub repo/mem:tools <github-url> <instructions>— Import with specific instructions (add/remove specific items)/mem:tools <instructions>— Directly add/remove/modify tools by prompt (no URL needed)/mem:tools(no args) — Show current registry stats and import help
Instructions
When the user invokes /mem:tools:
With GitHub URL
- Call
mem_registry(action="import_url", url="<github-url>", enrich=true)to import all skills/agents - The import pipeline automatically:
- Fetches repo file tree via GitHub API
- Discovers SKILL.md/AGENT.md files
- Parses frontmatter and extracts metadata
- Downloads files to managed/ directory
- Runs LLM enrichment for semantic tags (when enrich=true)
- Report imported tools in a table format
With GitHub URL + instructions
If the user provides instructions after the URL:
- "only add the TDD skill" → import only matching tools from that repo
- "remove the old testing tool" → call
mem_registry(action="remove", ...) - Follow user instructions for selective add/remove/modify operations
With instructions only (no URL)
If the user provides a prompt without a GitHub URL, parse the intent:
Adding a tool:
- "添加一个叫 my-linter 的 skill" or "add a skill called my-linter"
- → Ask for metadata (or infer from context): capability_summary, intent_tags, domain_tags, trigger_patterns
- → Call
mem_registry(action="import", name="my-linter", resource_type="skill", ...)
Removing a tool:
- "删除 old-testing skill" or "remove the old-testing agent"
- → Call
mem_registry(action="remove", name="old-testing", resource_type="skill")
Listing/searching:
- "有哪些 testing 相关的工具" or "list all agents"
- → Call
mem_registry(action="list", type="agent")or search by keywords
Modifying a tool:
- "更新 my-linter 的描述" or "update tags for my-tool"
- → Call
mem_registry(action="import", ...)with updated metadata (upsert)
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.
- 4d ago First seen · 68 lines · 25 tokens per session scan A dde2a8078d5e
tools is a command published in the GitHub repository sdsrss/claude-mem-lite (56 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 620 once invoked, about $0.0001 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
scope
Search your Claude Code session history (full-text, always fresh).
prime
Load project context and output a structured summary.
smartcompact
Pin important turns before compacting — pins survive compaction via SessionStart hook reinjection.
claudemd-bypass-audit
R3 Step 2 — lesson-bypass detector. Joins memory-prompt-hint suggest events with subsequent transcript activity to compute cite-recall (applied / (applied + bypassed)) across recent sessions. Makes the §11 MEMORY.md read-the-file effectiveness observable.
claudemd-doctor
Run health checks on claudemd installation. Flags missing deps, spec drift, settings.json issues, hook drift, backup inventory, rule-usage health, MEMORY.md tag specificity, cross-layer memory maintenance (promote/repatriate/stale candidates). Supports --prune-backups=N.
dream
Consolidate and reorganize project memory.