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 rag-curategit 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/rag-curate)<a href="https://agentmods.dev/skills/lucassantana-dev/sharekit/rag-curate"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/rag-curate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lucassantana-dev/sharekit/rag-curate"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/rag-curate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00065 | $0.01112 |
| Opus 5.5 | $0.00026 | $0.00445 |
| Sonnet 5.5 | $0.00013 | $0.00222 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade B, and why
rag-curate scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat > ~/.claude/standards/new-pattern.md <<'EOF' How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAG Curate
Add missing docs or rewrite weak chunks after a diagnostic (rag-quality, adt-rag-coverage, adt-rag-drift) identifies a gap. Surgical alternative to a full rebuild.
Corpus directories
| Type | Path |
|---|---|
| Skills | ~/.claude/skills/ |
| Standards | ~/.claude/standards/ |
| Plans | ~/.claude/plans/ |
| Codex | ~/.claude/codex/ |
| Handoffs | ~/.claude/handoffs/ |
| Code | tracked repos in build.py |
Three curation patterns
A. Missing doc → write + incremental reindex
mount | grep -q "${DEV_ROOT}" || { echo "BLOCKED: External HD unmounted — RAG index unreachable"; exit 1; }
cat > ~/.claude/standards/new-pattern.md <<'EOF'
# New Pattern Name
...
EOF
cd ~/.claude/rag-index
venv/bin/python build.py --incremental ~/.claude/standards/new-pattern.md
sqlite3 index.sqlite "SELECT COUNT(*) FROM chunks WHERE path LIKE '%new-pattern.md%';"
Done when: SELECT COUNT confirms >0 chunks indexed for the new doc.
Stop if: chunks count returns 0 — reindex failed or doc was filtered.
B. Weak retrieval (cos <0.40) → rewrite
mount | grep -q "${DEV_ROOT}" || { echo "BLOCKED: External HD unmounted — RAG index unreachable"; exit 1; }
cd ~/.claude/rag-index
venv/bin/python query.py "your weak query" --top 3
# note path + chunk id; edit the source file to add keywords / clarify context
venv/bin/python build.py --incremental <path>
venv/bin/python query.py "your weak query" --top 3 # cosine should rise
Done when: cosine score ≥0.40 for the weak query in top 3 results.
Stop if: score remains <0.40 after rewrite — content may not address the gap.
C. Undercovered repo → widen globs in build.py
mount | grep -q "${DEV_ROOT}" || { echo "BLOCKED: External HD unmounted — RAG index unreachable"; exit 1; }
sqlite3 ~/.claude/rag-index/index.sqlite \
"SELECT repo, COUNT(*) FROM chunks WHERE repo='your-repo' GROUP BY repo;"
grep -n "your-repo" ~/.claude/rag-index/build.py
# add globs (e.g. add 'src/**/*.tsx'), then incremental reindex
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.
- 1mo ago First seen · 116 lines · 65 tokens per session scan B d7e5a804401e
rag-curate is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 1,112 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
molecular-rag
Retrieve structurally similar compounds with known properties from ChEMBL/ZINC to ground predictions and inform optimization. Based on MolRAG (Xian 2025, ACL).
llmwiki
Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation. Use for llmwiki projects, retrieving reusable evidence for an agent task, or compiling a corpus for repeated questions. A one-off file read or live web search does not need a wiki.
bailian-cli
A command-line hub for Alibaba Cloud Bailian and DashScope resources. It covers applications, models, knowledge bases, usage, authentication, files, MCP services, pipelines, and installing or updating related agent skills.
bailian-kb
A command-line manager for Alibaba Cloud Bailian knowledge bases, which are collections of documents prepared for search and question answering. It handles the stored documents, search services, text chunks, and data-centre files rather than everyday searches.
llm-application-dev
Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…