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.
git clone --depth 1 https://github.com/skymanbp/rag-your-codeWrote 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/commands/skymanbp/rag-your-code/index)<a href="https://agentmods.dev/commands/skymanbp/rag-your-code/index"><img src="https://agentmods.dev/badge/commands/skymanbp/rag-your-code/index/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/commands/skymanbp/rag-your-code/index"><img src="https://agentmods.dev/badge/commands/skymanbp/rag-your-code/index.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 | $0.00031 | $0.00470 |
| Opus 5.5 | $0.00012 | $0.00188 |
| Sonnet 5.5 | $0.00006 | $0.00094 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
index 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.
What it actually says
/rag-your-code:index
Build or refresh the local retrieval index, and say what the repository still needs before search is actually good.
What to do
-
Make sure the package is importable. A plugin install copies these commands but not the Python package, so check once per machine. Use
python -m pipso it lands in the interpreter the later commands run under.python -c "import ragyourcode" || python -m pip install --user rag-your-code -
Run bootstrap against
$ARGUMENTSif the user named a path, otherwise.:python -m ragyourcode.cli bootstrap .Use
--fullonly after a parser or schema upgrade, or suspected corruption — the default incremental path reuses unchanged files.--compactis a flag onindex, not onbootstrap; a repository already built withindex --compactstays compact when bootstrap refreshes it. -
Report back three things, briefly:
- how many declarations were indexed, and whether the run was incremental;
- the rung bootstrap named, in plain language;
- any warnings or files it could not parse.
Why the rung matters
Indexing is not the same as being searchable. A fresh index retrieves against a
sentence the parser generated from identifiers the author already chose, so it
adds no word the source did not have — a question phrased in domain terms
reaches nothing. Say so explicitly if descriptions are pending, and offer
/rag-your-code:describe, because this is where most of the available
retrieval quality still sits and the user has no other way to learn it.
If the repository is indexing files it should not — a vendored tree, generated output — that is configuration, not something to work around:
python -m ragyourcode.cli config set index.ignore '["vendor", "generated"]'
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 · 53 lines · 31 tokens per session scan A 1ee54c51c626
index is a command published in the GitHub repository skymanbp/rag-your-code (1 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 470 once invoked, about $0.0001 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 commands, from other repositories
rag-tune
Audit a RAG pipeline for retrieval quality and cost, and emit prioritized concrete fixes.
new-rag
Scaffold a new RAG (Retrieval-Augmented Generation) pipeline with best practices.
ingest
Ingest a URL, directory, or file into your knowledge base. remember = a specific durable fact, ingest = a URL, learn = a distilled lesson that gets retrieval preference.
index-codebase
Index the project's source code for semantic search.
agent
Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.
inference.embed
Embed one or more texts into vectors.