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/thisisyoyodev/claude-rag/asknpx skills add ThisisYoYoDev/claude-rag --skill askgit clone --depth 1 https://github.com/ThisisYoYoDev/claude-ragWhat 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 | $0.00022 | $0.00377 |
| Opus 5 | $0.00011 | $0.00188 |
| Sonnet 5 | $0.00004 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade B, and why
ask scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/plugins/claude-rag/config.json 2>/dev/null || echo '{"connection":{"endpoint":"https://api.clauderag.io"}}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(curl *) What it actually says
RAG Ask
Answer the user's question using RAG context: "$ARGUMENTS"
Instructions
-
Read the plugin config to get the backend endpoint:
cat ~/.claude/plugins/claude-rag/config.json 2>/dev/null || echo '{"connection":{"endpoint":"https://api.clauderag.io"}}' -
Search the RAG database for relevant context:
curl -s -X POST <endpoint>/api/v1/search \ -H "Content-Type: application/json" \ -d '{"query": "<user_question>", "limit": 10, "threshold": 0.4}' -
Synthesize an answer based on the search results:
- Combine information from multiple results to form a coherent answer
- Cite specific sessions, tools, and dates when referencing past work
- If the answer comes from code (tool_result from Read), include relevant code snippets
- If results are from sub-agents, mention which agent type found the information
- Be transparent about confidence: if results have low scores (<0.5), caveat accordingly
-
Structure the response:
- Start with the direct answer
- Follow with supporting evidence from RAG results
- End with "Sources" listing the sessions/events referenced
-
If insufficient context is found:
- Say clearly that the RAG database doesn't have enough context
- Suggest what the user could search for instead
- Offer to answer from general knowledge (without RAG)
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.
- 2d ago First seen · 43 lines · 22 tokens per session scan B ad7e0674f8f4
ask is a skill published in the GitHub repository ThisisYoYoDev/claude-rag (9 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 377 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.