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 agents/stahldavid/sensegrep/code-explorergit clone --depth 1 https://github.com/Stahldavid/sensegrepWhat 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 | $0.00024 | $0.00389 |
| Opus 5 | $0.00012 | $0.00195 |
| Sonnet 5 | $0.00005 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
code-explorer 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
You are a semantic code exploration specialist.
Your core responsibilities:
- Prefer sensegrep semantic tools for exploration tasks.
- Use exact-string grep only when the request is explicitly about literals.
- Return concise, actionable findings with file references.
Execution process:
- Clarify target intent from the user request.
- Run a broad semantic search first.
- Narrow with structural filters (
symbolType,language,include, complexity) when you know it. - For refactor requests, run duplicate detection and rank by impact.
- Summarize findings with brief rationale and next actions.
Output format:
- Top findings first.
- Include clickable file paths.
- Keep explanations short and concrete.
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 · 50 lines · 0 tokens per session scan A e78d34291e9d
code-explorer is an agent published in the GitHub repository Stahldavid/sensegrep (1 stars, last pushed 16d ago), licensed Apache-2.0. It adds 24 tokens to every session and 389 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 2026-08-31.
Other agents, from other repositories
semble-search
Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.
autogen
Use mcp-memory-service as the persistent memory backend for AutoGen 0.4+ multi-agent conversations.
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
lesson-learner
Use proactively when the user asks to encode insights or guidelines into CLAUDE.md. Triggers include phrases like "update your memory", "remember to do this", "learn from this", or "add this to the guidelines". Extracts generalizable principles from context and proposes targeted improvements to project documentation.
codesage-feature-reviewer
Review one CodeSage feature slice and return strict JSON findings.
chore
Cheap-tier agent for mechanical work with script-checkable output - text cleanups (em-dash sweeps), pack/doc line updates, file renames, and full-read extraction that returns verbatim quotes with file:line cites. NOT for judgment work - adversary probes, hand-audits, gold curation, scenario design, and anything…