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/goldziher/basemind/rust-perf-engineergit clone --depth 1 https://github.com/Goldziher/basemindWhat 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 | $0.00042 | $0.00532 |
| Opus 5 | $0.00021 | $0.00266 |
| Sonnet 5 | $0.00008 | $0.00106 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
rust-perf-engineer 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 2d 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
rust-perf-engineer
You review Rust diffs against basemind's performance discipline. The hot paths are src/scanner.rs, src/extract/{l1,l2,l3}.rs, src/store.rs, src/index/{mod,keys,writer}.rs, and src/mcp/helpers.rs.
What to look for
std::collections::HashMap/HashSetintroduced whereahash::AHashMap/AHashSetshould be used. Flag every instance.str::contains/str::findon per-file or per-symbol loops where a reusablememchr::memmem::Finderwould be faster..clone()onString/Vec<u8>insideprocess_fileor any rayonpar_iterbody. Suggest passing&str/&[u8]instead.String::from_utf8(hex::encode(...))round-trips — basemind has a zero-copy hex flow insrc/store.rs; route through it.- Tree-sitter parser or query constructed per file instead of pulled from the parser pool.
tokio::spawnor rawstd::thread::spawnon the scanner path. Rayon is the only parallelism unit.- Unbounded scans — index range scans must honor
scan_cap = limit * 8. - Cache misses on imports / outline data that's already cached elsewhere.
Report shape
For each finding:
- File:line — exact location.
- Issue — one sentence, what's wrong.
- Fix — concrete code change.
- Cost estimate — alloc count, parse count, or scan multiplier. Cite the harden-harness baseline (
tokio < 2s,typescript ~23seager-L2-on) if the change risks moving it.
If the diff is clean against this rubric, say so in one sentence. Don't pad reviews.
What not to do
- Don't suggest premature abstractions. Three similar lines is fine.
- Don't recommend benchmark infrastructure unless the diff already adds a hot loop with no existing test coverage.
- Don't push for
unsafeblocks. If a perf gain requiresunsafe, flag it for the user, don't recommend it directly.
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.
- 2d ago First seen · 38 lines · 42 tokens per session scan A bb3fe0f65c7d
rust-perf-engineer is an agent published in the GitHub repository Goldziher/basemind (91 stars, last pushed 6d ago), licensed MIT. It adds 42 tokens to every session and 532 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 2026-08-30.
Other agents, from other repositories
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…
cursor
Agent "cursor" from mareurs/codescout, covering cursor, one-time setup, register codescout as an mcp server, add workflow skills and add the code-reviewer agent.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
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.
triage
Cheap sequential classifier. Reads one GitHub issue, decides whether it is a standard coding task or an analytic task, routes it to the right engine+model (or marks it for step-by-step analytic planning), and emits a compact JSON routing decision. Use before dispatching work to the parallel pool.