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/sagarmk/beacon-plugin/search-codegit clone --depth 1 https://github.com/sagarmk/beacon-pluginWhat 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 | $0.00010 | $0.00381 |
| Opus 5 | $0.00005 | $0.00191 |
| Sonnet 5 | $0.00002 | $0.00076 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
search-code 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.
What it actually says
/search-code
Search the codebase using Beacon hybrid search (semantic embeddings + BM25 keyword matching + identifier boosting).
Single query
- Run
node ${CLAUDE_PLUGIN_ROOT}/scripts/search.js "$ARGUMENTS" - Parse the JSON results — each match has
file,lines,similarity,score, andpreview - Review the
previewfield first — it often contains enough context to answer the query - Only read the actual source files if the preview is insufficient to answer the question
- Summarize findings and cite file:line references
Multi-query batch
Pass multiple quoted queries for a single HTTP round-trip:
node ${CLAUDE_PLUGIN_ROOT}/scripts/search.js "auth flow" "session handling"
Returns [{query, matches}, ...] grouped by query.
Options
--top-k N— number of results (default: 10)--threshold F— minimum score cutoff (default: 0.35)--path <prefix>— scope results to files under a directory (e.g.--path src/middleware/)--no-hybrid— disable hybrid scoring, use pure vector search
Result fields
file— file pathlines— matched line range (e.g. "45-78")similarity— vector cosine similarityscore— final hybrid score (semantic + BM25 + identifier boost)preview— first 300 chars of matched code chunk
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 · 37 lines · 10 tokens per session scan A 74c8ba0a46e5
search-code is a command published in the GitHub repository sagarmk/beacon-plugin (43 stars, last pushed 11d ago), licensed MIT. It adds 10 tokens to every session and 381 once invoked, about $0.0001 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 commands, from other repositories
rp-build-cli
Build with rp-cli context builder → chat → implement.
rp-investigate-cli
Deep codebase investigation and architecture research with rp-cli commands.
rp-oracle-export-cli
Export context for oracle consultation using rp-cli.
rp-reminder-cli
Continue your current workflow using rp-cli instead of built-in alternatives.
call-graph
Trace callers, callees, or paths using the call graph.
index
Index the codebase for semantic search.