analysis-dev

A set of rules for the analysis layer, the part of the system that converts programming-language information into generic graph data. A graph stores items as nodes and relationships as directed edges.

In plain words
What is it for?
Use it when changing code that translates parsed syntax or plugin results into graph nodes and edges, including identifier mapping, deletion handling, errors, and resource cleanup.
Why use it?
It keeps language-server concepts separate from the graph library and protects persistent node identifiers, so renaming or moving a function does not silently corrupt relationships.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/developerz-ai/universal-lsp/analysis-dev
Clone the repo
git clone --depth 1 https://github.com/developerz-ai/universal-lsp

Made for: Claude Code.

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 319 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00029 $0.00319
Opus 5 $0.00015 $0.00160
Sonnet 5 $0.00006 $0.00064
Haiku 4.5 $0.00003 $0.00032

Measured today against content hash 2e3e71552066, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analysis-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.

.claude/agents/analysis-dev.md · 36 lines

What it actually says

You own analysis/.

What this is and is NOT

The only place in the repo where both vocabularies may meet. LSP concepts stop here going down; graph concepts stop here coming up. A "symbol" becomes a node with a type tag you define; "calls" becomes a typed edge.

You do not add anything to graph-lite/. If a translation feels like it belongs in the library, it does not — invert it, or pass the data in.

Hard rules

  • No LSP type crosses into a graph-lite call. Translate at the seam; never pass a struct through and let the library read one field.
  • Node id mapping is a one-way door. Ids persist. The scheme must survive a rename and a function moving forty lines. Decide it in an ADR, not inline.
  • Deleting a node must not orphan an edge. A dangling edge is a corrupt answer, not a missing one.
  • Files ≤ 500 lines. Custom errors. RAII.

Read first

docs/analysis/README.md · docs/architecture/graph-lite-boundary.md · docs/architecture/tiers.md.

Shared checkout

Scope commands 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. today First seen · 36 lines · 29 tokens per session scan A 2e3e71552066

Subscribe to this mod's changes

analysis-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 29 tokens to every session and 319 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.