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/cq27-dev/rag-rat/init-rag-ratnpx skills add cq27-dev/rag-rat --skill init-rag-ratgit clone --depth 1 https://github.com/cq27-dev/rag-ratWrote 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/cq27-dev/rag-rat/init-rag-rat)<a href="https://agentmods.dev/skills/cq27-dev/rag-rat/init-rag-rat"><img src="https://agentmods.dev/badge/skills/cq27-dev/rag-rat/init-rag-rat.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 | $0.00224 | $0.01963 |
| Opus 5 | $0.00112 | $0.00981 |
| Sonnet 5 | $0.00045 | $0.00393 |
| Haiku 4.5 | $0.00022 | $0.00196 |
Grade A, and why
init-rag-rat 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 4d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
init-rag-rat — configure a dormant rag-rat repo conversationally
rag-rat's MCP server boots dormant in a repo with no rag-rat.toml: ordinary tools return
{"status":"no_index", "remedy":"Run rag-rat init … then restart"}. This skill turns that into a
short guided setup. You own the conversation; rag-rat init owns the scan and validation — never
hand-write a config blind, and let a real config load re-check it before indexing.
The common path
-
Detect state. You are here because a rag-rat tool returned
status: "no_index", or the user asked to set up rag-rat. Confirm there is norag-rat.tomlat (or above) the repo root. If one already exists, this is a reconfigure — send the user to the interactiverag-rat initwizard and stop. -
Resolve the CLI and use the same form throughout, from the target repo's root. It must match the version the rag-rat MCP server runs, so the index you create is one the server can read — do not use
@latest, and don't blindly trust an on-PATHrag-rat:- If
rag-ratis onPATH, checkrag-rat --versionand use it only if it matches the plugin/MCP version — a stale global install would build the index with the wrong binary. - Otherwise (or on a version mismatch) use
npx -y @rag-rat/[email protected] …— the plugin pins@rag-rat/binto its own version and caches the binary privately, so this is the version-matched CLI;npxruns it in the current directory.
- If
-
Dry-run discovery.
<rag-rat> init --yes --dry-runscans the repo and prints the auto-detected config (languages, path bindings, the default local FastEmbed backend) without writing. Read it; tell the user the material bits in a line or two (which languages and directories) — not every commented knob. -
Default to FastEmbed unless the machine is powerful (or the repo is large). FastEmbed (all-MiniLM, 384-dim, local CPU) needs zero setup and is the right call for most repos on a modest workstation. Recommend it by default. Only raise a remote / GPU embedder when it earns its keep: a large repo, a wish for a stronger code-specific embedder, or an available GPU / cloud budget.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 108 lines · 224 tokens per session scan A 38b708d3fa9b
init-rag-rat is a skill published in the GitHub repository cq27-dev/rag-rat (19 stars, last pushed 6d ago), licensed MIT. It adds 224 tokens to every session and 1,963 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
vault-for-llm
Connect OpenClaw to Vault Agent Memory as a local-first governed project memory layer. Search first, then bounded-read cited source ranges; propose new memories as candidates instead of writing directly into active memory.
skills
Your next session starts cold. No memory of what you built, what broke, what you decided. Every memory you write is a gift to that future session. The richer the memory, the less time re-learning.
any-mcp
Use when an agent needs to read, search, create, edit, organize, upload, or chat with Anytype through the bounded any-mcp server. Covers safe tool selection, exact identifier chaining, optional toolsets, common PKM workflows, and the narrow anyr fallbacks for chat subscriptions and rich chat blocks.
alice-memory
Use Alice as the user's durable local memory. Load before answering from context, and whenever you learn something worth keeping across sessions.
alice-project-memory
Use Alice as the project-scoped memory and continuity layer. Load before build or review work, and whenever a decision or constraint is worth keeping.
alice-continuity-recall
Use Alice MCP recall tools for continuity-grounded answers with provenance when users ask what was decided, what changed, or what to remember.