Borrowing it
Nothing to install: this file belongs to azmirizkifar20/RAGBuddy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/azmirizkifar20/RAGBuddy/main/.agents/skills/ragbuddy-feature-flow/SKILL.mdgit clone --depth 1 https://github.com/azmirizkifar20/RAGBuddyWrote 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/azmirizkifar20/ragbuddy/ragbuddy-feature-flow)<a href="https://agentmods.dev/skills/azmirizkifar20/ragbuddy/ragbuddy-feature-flow"><img src="https://agentmods.dev/badge/skills/azmirizkifar20/ragbuddy/ragbuddy-feature-flow/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/azmirizkifar20/ragbuddy/ragbuddy-feature-flow"><img src="https://agentmods.dev/badge/skills/azmirizkifar20/ragbuddy/ragbuddy-feature-flow.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 | $0.00043 | $0.01032 |
| Opus 5.5 | $0.00017 | $0.00413 |
| Sonnet 5.5 | $0.00009 | $0.00206 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
ragbuddy-feature-flow 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 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.
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAGBuddy Feature Flow
Follow this flow for feature work in this repository.
0. Project status
RAGBuddy is currently pre-implementation — only init.md (the full build spec) and the docs/ scaffold exist. Every doc in docs/features/ is marked Planned. When you implement a phase from init.md §26, flip that feature doc's status from Planned to Implemented and fill in its real file paths (see step 5).
1. Read the current-state docs first
- Start by checking docs/features/README.md.
- Find the most relevant existing (or planned) doc with repo terms before coding.
- Also check docs/steering/ for architecture, routing (CLI/MCP), tech-stack, and system-flow context.
- Cross-check against init.md itself — it is the authoritative spec until the docs are updated to reflect real implementation.
2. Trace the real runtime path
- Prove the implementation path from the repo, not from assumptions. Once code exists, trace actual imports/calls rather than trusting a planned-doc path.
3. Add or update tests when they materially protect the change
- Treat test evaluation as part of the implementation, not optional follow-up.
- Priority order per
init.md§23: project registry, scanner, hashing, chunking, sync (add/modify/delete/unchanged), security (path traversal, cross-project isolation), MCP tools. - Mock Qdrant and the embedding provider in unit tests — do not require a real embedding provider or live Qdrant instance (
init.md§23). - Do not force tests for every low-risk edit (copy tweaks, trivial wiring). When you choose not to add tests, state the reason in the completion summary.
4. Verify the changed path
- Test runner: Vitest (per spec —
init.md§3). Exact command TBD oncepackage.jsonis created; expectednpm test/npx vitest run. - If no test was added because the change was low-value to cover, verify the path with another focused check matching the risk (manual CLI run, targeted command).
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 · 67 lines · 43 tokens per session scan A 48cf19717af6
ragbuddy-feature-flow is a skill published in the GitHub repository azmirizkifar20/RAGBuddy (2 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 1,032 once invoked, about $0.0002 per session on Opus 5.5. 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
llm-security
Use for authorized security assessment of LLM applications and AI agents, including prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.
graph-retrieval
Exposes graph-based retrieval as a tool capability via querygraph. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.
knowledge-layer
High-level deployment wrapper over RepoBrain core with graph-first knowledge injection and all-file support. Exposes refreshfilesystem and askfilesystem for building and querying the knowledge graph.
haiku-rag
Search, read and compute over the user's haiku.rag knowledge base through the haiku-rag MCP tools. Use whenever a request could be answered from the user's ingested documents, when asked to find, look up, check or cite something in their documents or knowledge base, or when the question is about the user's own…
opik-evaluate
Build an LLM evaluation and run it against the app, returning an Opik experiment with scores and its link. Picks a test suite with judge assertions or a dataset with metrics, sources cases from traces or synthetic data, scores heuristics-first then one-failure-mode judges, runs client-side via the SDK or server-side…
vector-backend-operations
Select and connect the right vector-store backend for the vector-mcp MCP server — chromadb, postgres/pgvector, qdrant, couchbase, or mongodb — and supply the correct dbtype/connection parameters that every collection and search call needs. Use when the agent must decide which engine to target, wire up…