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 skills add LucasSantana-Dev/sharekit --skill recallgit clone --depth 1 https://github.com/LucasSantana-Dev/sharekitWrote 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/lucassantana-dev/sharekit/recall)<a href="https://agentmods.dev/skills/lucassantana-dev/sharekit/recall"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/recall.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 | $0.00121 | $0.01041 |
| Opus 5 | $0.00060 | $0.00521 |
| Sonnet 5 | $0.00024 | $0.00208 |
| Haiku 4.5 | $0.00012 | $0.00104 |
Grade A, and why
recall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
recall
Single-shot RAG lookup. Don't over-fetch.
Mount guard: [ -d "${DEV_ROOT}/rag-index" ] || echo WARNING: RAG degraded - directory reachability, not mount output parsing (matches the canonical guard in claude/skills/knowledge-loop/references/mount-guard.sh: mount only lists actual mount points, never nested paths, so grepping its output false-positives as "unmounted" even when the drive is present; it also escapes spaces in mount-point paths on Linux, which a naive grep won't decode). The index lives on the external drive; an unmounted drive silently degrades recall. See standards/knowledge-brain.md §1.
How
Call the MCP tool directly:
rag_query(query="<natural-language question>", top=5)
Done when: top results answer your question in 1–2 chunks. If not, narrow the query or increase top (up to 8).
Optional args:
top(1–20, default 5) — more isn't always better; reranker quality drops past 8.scope_types— narrow to e.g.["memory", "handoffs"]for "what did I write down" queries, or["commit"]for "what did we ship lately on X".scope_repos— pass["all"]to ignore cwd auto-scope; pass["<project-a>"]etc. to force a specific repo.
Failure modes
- Unmounted external drive — if the drive drops mid-session, the RAG index becomes stale or inaccessible. Mount guard (above) catches this; surface "WARNING: RAG degraded" and skip the query or fall back to grep.
- Stale index — if memory or code changed recently and the reindex hook hasn't run (2–5 minute lag typical), you may miss the latest decisions or commits. Fallback: ask directly ("what did we just decide") or grep recent files /
git log. - Low-quality rerank — if you ask a vague question ("fix this") without context, the reranker may return false positives. Be specific ("why did we choose D1 for Progress Tracker storage").
Anatomy of results
A rag_query() result includes:
{
"results": [
{
"text": "<chunk content>",
"source": {
"type": "memory" | "handoff" | "plan" | "commit" | "code" | "readme",
"repo": "<project-a>" | "<homelab>" | "...",
"path": "..."
},
"score": 0.87 // reranker confidence; >0.8 usually relevant
}
]
}
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 · 79 lines · 121 tokens per session scan A a2fe294ded68
recall is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 7d ago), licensed MIT. It adds 121 tokens to every session and 1,041 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
memory-optimization
Tune moflo's memory stack for speed, RAM, and index quality. Covers HNSW parameters (M, efConstruction, ef), vector quantization, batch operations, and common bottlenecks. Use when scaling past 100k entries or when search latency regresses.
qmd-mcp-skill
Use a local QMD knowledge base through UXC over MCP stdio, with daemon-backed session reuse and typed retrieval flows that avoid repeated model warmup and unnecessary query-expansion latency.
bedrock-rag
Build RAG on Amazon Bedrock Knowledge Bases — ingestion, chunking, embeddings, vector stores, Retrieve and RetrieveAndGenerate, citations, and Guardrails contextual grounding. Use when a chatbot must answer from a document corpus with sources.
google-adk-python
Build AI agents with Google Agent Development Kit (ADK) for Python. Use when creating multi-agent systems, tool-using agents, or orchestrating LLM workflows with Google Cloud.
ai-automation
Workflow automation skills using AI. Build chatbots, automate repetitive tasks, integrate LLMs into pipelines, design intent-based assistants. Triggers on: chatbot, automation, workflow, AI agent, RAG, LLM integration, intent recognition, conversation design.
Cursor rules for Next
Cursor rules for Next.js development with Tailwind CSS and TypeScript integration.