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 skills/viknesh20-20/claude-code-tool-kit/memory-importnpx skills add viknesh20-20/claude-code-tool-kit --skill memory-importgit clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kitWrote 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/skills/viknesh20-20/claude-code-tool-kit/memory-import)<a href="https://agentmods.dev/skills/viknesh20-20/claude-code-tool-kit/memory-import"><img src="https://agentmods.dev/badge/skills/viknesh20-20/claude-code-tool-kit/memory-import.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 | $0.00055 | $0.01022 |
| Opus 5 | $0.00028 | $0.00511 |
| Sonnet 5 | $0.00011 | $0.00204 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
memory-import 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 3d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/memory-import
Pull memories from another workspace into the current one. Useful when the user has built a previous app and wants its accumulated context — conventions, gotchas, references — to inform a new project.
When to use
- Starting a new project that's similar to one the user already built.
- Doing a code review on a project where the user wants you to reference patterns from another of their projects.
- Onboarding to a new repo where the team's conventions are already documented in another workspace.
Operating method
-
Validate the source path. Check that
<path>/.claude/memory/MEMORY.mdexists. If not, tell the user the source workspace doesn't have a memory layer (it may not have been initialized with this toolkit). -
Read the source's memory index and the files it references.
-
Categorize what to import. For each memory:
- Always copy
project/andreference/(with provenance tag) — they're the most likely to inform the new project. - Ask before copying
feedback/— preferences from another project may not transfer ("no Tailwind in app A" doesn't mean "no Tailwind in app B"). Show the user the list and let them check/uncheck. - Ask before copying
user/— usually applies (it's about the user, not the project), but the user should confirm. - Skip
handoffs/— those are session-specific to the source workspace. - Skip
inherited/— don't transitively chain inherits. If the user wants those too, they can re-import from the original source.
- Always copy
-
Show a preview. List the memories you intend to import, grouped by type. Ask: "Import these ?"
-
Copy with provenance. Each imported memory gets:
- Filename prefixed with the source workspace name:
inherited/<source>-<original-filename>.md. - Frontmatter
source-workspace: <path>added. - A header line in the body:
> Imported from <source> on <date>. Treat as suggestive, not authoritative for the current project.
- Filename prefixed with the source workspace name:
-
Update the index. Add lines to
.claude/memory/MEMORY.mdunder "Inherited (from other workspaces)."
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.
- 3d ago First seen · 86 lines · 55 tokens per session scan A bf4bbb40a1ea
memory-import is a skill published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 1,022 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
faq-mine
Mine docs/faq.md from README.md, docs/.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when asked to "build / regenerate / extend the FAQ", "mine docs into FAQ", "mine hermes memory into FAQ", "surface runtime…
claude-compaction-restore
Use when a Claude Code session has just compacted, is about to compact, reached context limit, resumed after /compact, or needs to rebuild its working mental model from Claude JSONL transcripts and touched files.
Ingest Source
Tiêu hoá một source thô vào Second Brain, chưng cất thành tri thức wiki tích luỹ.
Lint Wiki
Rà soát sức khoẻ wiki của Second Brain, trả về danh sách vấn đề. Không tự sửa hàng loạt.
lore
Curating cross-agent knowledge and institutional memory: extracts patterns from agent journals into METAPATTERNS.md, detects knowledge decay, propagates best practices. Use for memory curation.
a2wave-memory
Progressively recall and maintain a2wave cross-session memory through a compact startup catalog, bounded topics, and searchable history.