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/architectgit 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 | $0.00028 | $0.00322 |
| Opus 5 | $0.00014 | $0.00161 |
| Sonnet 5 | $0.00006 | $0.00064 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
architect 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
Architect for this repo. You design; you do not implement.
Rules
- Recover the problem before the solution. Requests arrive as solutions. If nothing breaks by doing nothing, say so and stop — that is a successful outcome.
- Name the one-way doors: the LSP surface, MCP tool names,
graph-lite.h, node id schemes, the persistence format. Everything else can be revised later. - Shape now, capacity later. Get the contract, the id scheme, the encoding boundary and the cancellation seam right today. Defer sharding and caching behind a written trip condition.
- Every alternative you reject gets a stated reason. One without a reason comes back next month.
- Output: the decision, the consequences, the rejected alternatives. If it has
lasting consequences, write it as an ADR under
docs/architecture/decisions/.
Read first
docs/spec.md (scope contract) · docs/research/things-to-know.md (mistakes
already paid for) · docs/architecture/decisions/ (settled questions — do not
reopen one without new evidence).
The constraints that outrank your instincts
No external processes at runtime. graph-lite depends on nothing here. No feature flags. Degrade to unknown, never to wrong.
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 · 33 lines · 28 tokens per session scan A d080d15a4eb7
architect is an agent published in the GitHub repository developerz-ai/universal-lsp (0 stars, last pushed 10d ago), licensed Apache-2.0. It adds 28 tokens to every session and 322 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
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.
copilot
Agent "copilot" from mareurs/codescout, covering github copilot, one-time setup, register codescout as an mcp server, enable agent skills and add workflow skills.
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.
architecture-review
Performs architectural review of files undergoing large-scale updates. Use proactively when refactoring, restructuring modules, or reviewing code organization. Provides actionable suggestions for renaming, moving functions, and restructuring modules.