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/developerz-ai/universal-lsp/engine-devgit clone --depth 1 https://github.com/developerz-ai/universal-lspWhat 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 | $0.00033 | $0.00434 |
| Opus 5 | $0.00016 | $0.00217 |
| Sonnet 5 | $0.00007 | $0.00087 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
engine-dev 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 today.
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 own engine/, daemon/, cli/, tests/engine/.
What this is and is NOT
The daemon core and its thin entrypoints. Business logic lives here; daemon/ and
cli/ are wiring only. Graph storage is not yours — it is a dependency.
Hard rules
- Never spawn, proxy to, or depend on an external language server, binary, or network service. That deletion is the product.
- Position offsets convert at the protocol boundary and nowhere else. UTF-16
code units exist on the wire; internally there is one encoding. Read
docs/engine/position-encoding.mdbefore touching anything that indexes text — this bug class panics production language servers on emoji. - Out-of-editor changes are the default case. An agent writing files sends no
didChange. Anything gated on protocol edit signals does not run for the primary user. Seedocs/engine/filesystem-changes.md. - Background work must be cancellable and superseded when its file becomes interactive. Without that the priority split is decorative.
- RAII for every lifecycle object. Custom errors. Files ≤ 500 lines. No warning suppressions.
Testing
TDD. Protocol decode and offset conversion are pure functions — test them
exhaustively, including astral-plane characters, \r\n, and end-of-file. Never
sleep(); inject the clock. Suites named engine_*.
Commands
bin/check --files engine/src/x.cpp tests/engine/x_test.cpp
bin/dev test engine
bin/dev asan # the memory bugs here read as wrong answers, not crashes
Shared checkout
Scope commands to your files. Concurrency 1. No git operations, never git stash.
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.
- today First seen · 47 lines · 33 tokens per session scan A ee23e4299f0b
engine-dev is an agent published in the GitHub repository developerz-ai/universal-lsp (0 stars, last pushed 9d ago), licensed Apache-2.0. It adds 33 tokens to every session and 434 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 agents, from other repositories
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
mcp-tool-author
Adds a mode to one of basemind's 9 MCP domains end-to-end — mode enum variant, params, shim arm, helper body, CLI subcommand, smoke assertion, README row.
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…
rust-perf-engineer
Reviews diffs touching the basemind scanner / extract / store / index paths for hot-path regressions — allocations, missed memmem opportunities, hashmap churn, parser pool misuse.