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 commands/skymanbp/rag-your-code/statusgit clone --depth 1 https://github.com/skymanbp/rag-your-codeWhat 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 | $0.00031 | $0.00548 |
| Opus 5 | $0.00015 | $0.00274 |
| Sonnet 5 | $0.00006 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
status 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 yesterday.
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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rag-your-code:status
Report whether search here can be trusted right now, and what would improve it.
What to do
python -m ragyourcode.cli describe status
python -m ragyourcode.cli config list
Then a live query, to prove retrieval actually answers rather than only that the files exist:
python -m ragyourcode.cli search "<something this repository certainly does>" --json --limit 3
What to report
Four things, in this order, and briefly:
-
Is the index current? Read it from a field rather than from a warning:
stale_indexindescribe status,staleinsearch --json.config listnever opens the index and reports nothing about it. Three different things make it stale and only one is a file edit: the repository content moved, the rules that decide what a unit is changed, or the written descriptions changed. Any of them means/rag-your-code:index. -
Description coverage — described, superseded and missing. Superseded is the interesting one: something was written about that declaration and the code has since changed, so it is deliberately not applied. Those are re-describe work, not lost work.
-
Which embedder is in force.
embedding.provideris one ofsigned-feature-hash(the default — offline, no dependency, matching is lexical),sentence-transformers(a model on this machine) oropenai-compatible(a service). Say which, because it changes what retrieval can reach. Do not switch it for the user: one adds a dependency and downloads weights, the other can send their source to a third party, and both are theirs to decide. -
The next useful move. Usually one of: refresh the index, run
/rag-your-code:describe, or narrowindex.ignoreif a vendored or generated tree is being indexed.
Do not tune the evidence bars
If searches come back empty, that is search.min_coverage and
search.min_concentration doing their job — refusing to hand back a plausible
wrong declaration. Lowering them restores guessing. Report low description
coverage instead; that is the real cause and the real fix.
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.
- yesterday First seen · 57 lines · 31 tokens per session scan A 6b343d718c5b
status is a command published in the GitHub repository skymanbp/rag-your-code (1 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 548 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
fieldtheory
Explain and drive the Field Theory CLI — bookmark-sourced seeds, repo-aware possibility runs that score ideas onto a 2x2 grid, and the interconnected .md files they leave behind. Trigger when the user asks about ft, bookmarks, seeds, ft possible (or the older name ft ideas), grids, dots/nodes, or how to turn saved…
rp-build-cli
Build with rp-cli context builder → chat → implement.
index
Index the codebase for semantic search.
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.
index
Visual overview of Beacon index — chunks, coverage, provider. Pass --files to list indexed files.
codesage-bench
Run CodeSage retrieval benchmarks on all corpora, save timestamped scorecards, print a summary.