universal-lsp: Agent for Claude Code

.claude/agents/graph-lite-dev.md

graph-lite-dev is an agent for Claude Code from developerz-ai/universal-lsp. It costs 29 tokens per session (417 once invoked), scanned A, original, Apache-2.0.

A set of rules for maintaining an embeddable property-graph library: software that stores typed nodes, typed directed relationships, and their properties. It also covers saving, loading, and traversing that data.

In plain words
What is it for?
Use it to change graph storage, traversal, or persistence, build the library on its own, update its public header, and test round trips, damaged files, crashes, and generated edge cases.
Why use it?
It keeps the library independent of the rest of the project and protects saved data from incompatible format changes. Test-driven development (TDD) means writing or defining tests as part of building each change.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is developerz-ai/universal-lsp's own configuration. It tells Claude Code how to work on universal-lsp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything universal-lsp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to developerz-ai/universal-lsp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/developerz-ai/universal-lsp/main/.claude/agents/graph-lite-dev.md
Clone the repo
git clone --depth 1 https://github.com/developerz-ai/universal-lsp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for graph-lite-dev

README.md
[![agentmods](https://agentmods.dev/badge/agents/developerz-ai/universal-lsp/graph-lite-dev/github.svg)](https://agentmods.dev/agents/developerz-ai/universal-lsp/graph-lite-dev)
Your own site
<a href="https://agentmods.dev/agents/developerz-ai/universal-lsp/graph-lite-dev"><img src="https://agentmods.dev/badge/agents/developerz-ai/universal-lsp/graph-lite-dev/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for graph-lite-dev

Your own site · 80×15
<a href="https://agentmods.dev/agents/developerz-ai/universal-lsp/graph-lite-dev"><img src="https://agentmods.dev/badge/agents/developerz-ai/universal-lsp/graph-lite-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 417 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.00417
Opus 5.5 $0.00012 $0.00167
Sonnet 5.5 $0.00006 $0.00083
Haiku 4.5 $0.00003 $0.00042

Measured 2mo ago against content hash b2d5df754223, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

graph-lite-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 2mo 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.

.claude/agents/graph-lite-dev.md · 46 lines

What it actually says

You own graph-lite/ and tests/graph-lite/. Nothing else.

What this is and is NOT

A generic property-graph library: typed nodes, typed directed edges, properties. It is not aware of what the rest of this repo does with it. If you are writing a domain concept here, you are in analysis/ and in the wrong workspace.

Hard rules

  • No consumer vocabulary anywhere — API, internals, tests, docs/graph-lite/. The guard tokenises CamelCase, so SymbolNode is caught too.
  • No #include of an engine header, no link against a repo target. It must build standalone.
  • graph-lite.h is a public contract. An addition is a promise.
  • Persistence changes: bump the format version, and refuse a newer file rather than reading it optimistically.
  • Files ≤ 500 lines. Custom error types. RAII. No naked new.

Testing

TDD. Persistence gets disproportionate investment — fuzzing, a truncation sweep, crash consistency (old state or new, never a third thing), round-trip properties. Register with ulsp_add_test, name suites graph_lite_*.

Commands (from the repo root)

bin/check --files graph-lite/src/x.cpp tests/graph-lite/x_test.cpp
bin/dev test graph_lite
cmake -S graph-lite -B build/graph-lite-standalone -G Ninja && cmake --build build/graph-lite-standalone

Read graph-lite/CLAUDE.md and docs/graph-lite/.

Shared checkout

Scope every command to your files. Concurrency 1. No git operations, never git stash.

Changes

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.

  1. 2mo ago First seen · 46 lines · 29 tokens per session scan A b2d5df754223

Subscribe to this mod's changes

graph-lite-dev is an agent published in the GitHub repository developerz-ai/universal-lsp (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 29 tokens to every session and 417 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

Other agents, from other repositories

dba

Database specialist adapting to any engine (PostgreSQL, SQLite, MongoDB, etc.) — schema design, query optimization, migrations, and index tuning.

cdeust/ai-architect-mcp-codebase · 33 tokens

devops-engineer

DevOps engineer for CI/CD pipelines, Docker, PostgreSQL provisioning, monitoring, and deployment.

cdeust/ai-architect-mcp-codebase · 23 tokens

jarvis-navigator

Answers multi-hop structural questions about an indexed repository by chaining jarvis MCP tools — goToDefinition, then callHierarchy, then blastRadius. Use when a question needs more than one navigation call, such as what breaks if a symbol changes or tracing a call path across repositories.

jarvis-intelligence/jarvis-index · 60 tokens

django-migrations-specialist

Database specialist for Django, runs in the "database" extra phase after development. Finalizes model field types and Meta indexes/constraints, runs makemigrations, reviews generated SQL with sqlmigrate, runs migrate, verifies with migrate --check. Do NOT use for: application logic (django-architect), tests…

AratKruglik/claude-sdlc · 85 tokens

database-architect

Use this agent for database design and change work: schema design, indexing strategy, query optimization, migration safety, and engine selection. Trigger on "design a schema for", "this query is slow", "is this migration safe", "add an index", "Postgres or Mongo for this", or N+1 complaints. Returns schema/DDL with…

aayushostwal/nexus · 96 tokens

type-reconstructor

Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…

marcosd4h/DeepExtractRuntime · 63 tokens