repo-intel

repo-intel

Unified static analysis for AI agents - git history, AST symbols, project metadata, doc-code sync, and (optionally) LLM-augmented file descriptors plus a 3-depth narrative summary, via a cached, incrementally-updatable Rust binary.

Part of the agentsys ecosystem.

Scan a repo once, cache the result, then query it repeatedly. The heavy lifting runs in the agent-analyzer Rust binary - this plugin provides the JavaScript interface, the skill layer that other plugins consume, and the orchestration that spawns Haiku subagents to enrich the artifact with semantic signals.

Why this plugin

• Use this when you need to identify high-churn files before a refactor
• Use this when evaluating bus factor risk across your codebase
• Use this when finding files that always change together (coupling)
• Use this when an agent (or you) needs a fast first-foothold in an unfamiliar repo (find <concept> and summary)
• Use this when other plugins need repo intelligence (deslop, sync-docs, drift-detect, audit-project, next-task, onboard, can-i-help)

Installation

agentsys install repo-intel

Quick start

/repo-intel init                          # Scan repo (first time, deterministic)
/repo-intel enrich                        # OPTIONAL: spawn Haiku agents to add descriptors + summary
/repo-intel query hotspots                # Most active files, recency-weighted
/repo-intel query find "auth flow"        # Concept search across files (uses descriptors when present)
/repo-intel query summary --depth=1       # One-sentence repo description (needs enrich)
/repo-intel query ownership src/auth/     # Who owns a path
/repo-intel query bus-factor              # Knowledge distribution risk
/repo-intel query painspots               # Hot x buggy x complex
/repo-intel query entry-points            # Where execution starts (binaries, mains, scripts)
/repo-intel query stale-docs              # Docs with stale symbol references

After init, the artifact is cached as repo-intel.json in the platform state dir (.claude/, .opencode/, or .codex/). Subsequent queries are instant. Run /repo-intel update to add new commits incrementally.

Actions

Action	What it does
init	Full scan - git history, AST symbols, project metadata, doc-code sync
update	Incremental update (only new commits since last scan)
enrich	Spawn the repo-intel-summarizer and repo-intel-weighter Haiku subagents to populate summary (3 depths) and fileDescriptors (top-500 most-active files). Also runs the embedder when opted in (see below). Optional - all deterministic queries work without it.
status	Check cache staleness - commits behind, last analyzed date
query <type>	Run a specific analysis query
embed status	Show embedder install state, variant + detail, sidecar info
embed update	Delta re-embed of changed files only (CI-friendly)
embed reset	Clear cached embedder preference; next enrich re-prompts

Query types

Activity

Query	Description
hotspots	Most-changed files, recency-weighted
coldspots	Least-changed files (unmaintained)
file-history <file>	Change timeline for a specific file

Quality

Query	Description
bugspots	Files with highest bug-fix density (fix commits / total)
test-gaps	Hot source files without co-changing test files
diff-risk <files>	Risk score for recently changed files
painspots	Hotspot x (1 + bug rate) x (1 + complexity/30) - requires AST data

People

Query	Description
ownership <path>	Who owns a path, with staleness flags
contributors	All contributors with commit counts and AI ratio
bus-factor	Knowledge concentration risk with at-risk areas

Coupling

Query	Description
coupling <file>	Files that always change together

Standards

Query	Description
norms	Detected commit conventions (conventional, freeform, mixed)
conventions	Commit style prefixes and scopes

Health

Query	Description
areas	Directory-level health (healthy / needs-attention / at-risk)
health	Repo-wide health overview
release-info	Release cadence and tag history

LLM-augmented (requires /repo-intel enrich first)

Query	Description
find <concept>	Concept-to-file search. With descriptors, catches synonyms (worker ↔ executor); without, falls back to deterministic substring scoring across paths/symbols/imports/doc-headers.
summary [--depth=1|3|10]	Cached 3-depth narrative description: one sentence / one paragraph / one-page technical overview.