Skill Claude CodeCodex
Use when the user relays an incoming stakeholder, client, or product request that should be captured as a written .context/requests/ item before anyone acts on it — a feature ask, a requirement from a meeting, user feedback to formalize. Fires on "the client asked for X", "the stakeholder wants X", "capture this as a…
Skill Claude CodeCodex
Use when the user needs to investigate, explore, or spike on how something works and the findings should land as written .context/research/ notes before any plan or implementation. Fires on "research how X works", "investigate X", "spike on X", "look into how X is done", "I need to understand X before planning". Not…
Skill Claude CodeCodex
Use when the user wants code reviewed as it stands — a module, a feature, a path, or the whole app — rather than a diff or a pull request. Covers correctness/bug hunting, simplification and dead code, exploitable security defects, and performance waste, and it first proposes which finder agents are worth launching and…
Skill Claude CodeCodex
Use when the user wants an existing or in-progress skill checked or structured against THIS project's house skill conventions — "what are our skill conventions", "review this skill against our standards", "does this skill follow our patterns", "structure this skill the way we do", "audit this skill's…
Skill Claude CodeCodex
Use when the user wants to design or scaffold a one-shot multi-agent fan-out / decomposition orchestration — review code across N dimensions, migrate N call-sites in parallel, research N sources, or split an implementation into parallel agents with per-agent model/effort assignment — landing as a written…
Skill Claude CodeCodex
Use when the user wants to create, run or tear down a git worktree with its own isolated environment (database, ports, containers), or when a project has no worktree setup yet and one needs bootstrapping by investigating the repo topology and verifying the compose stack can run twice — "set up a worktree for X"…
Skill Claude CodeCodex
Use when the user wants to audit, organize, clean up, or health-check their Claude Code setup — a messy or inconsistent .context/, a bloated or stale MEMORY.md, broken symlinks in .claude/skills, unused or misplaced skills, dead CLAUDE.md links, plugins inflating idle context, or "my project opens heavy / wastes…
Agent
Audits .context/ project content (references, docs, plans, issues, roadmap, requests, decisions, audits) for structural compliance.
Agent
Parses pasted /context breakdown and cross-references it with skills, MEMORY.md, CLAUDE.md, and plugins to produce a priority-ordered list of token savings.
Agent
Runs the aidex-conventions validator (validate.py) against the project's .context/ and reports violations as aidex findings.
Agent
Detects stale documentation by comparing Last Updated dates against recent project activity.
Agent
Audits MEMORY.md for bloat, stale entries, dead links, duplicates, orphan files, decisions overlap, and contradictions between feedback and project memories.
Agent
Audits installed Claude Code plugins for always-loaded subagent cost vs. recent usage; flags uninstall candidates.
Agent
Audits skills across all scopes for structural issues, frontmatter compliance, and scope placement.
Agent
Verifies all symlinks in .claude/ resolve to valid targets.
Plugin Claude Code
Plugin marketplace listing 1 plugin: dt.
Plugin Claude Code
DomainTome — living knowledge graph for software projects. Bundles the MCP server, auto-invoked read/write skills, and /dt: slash commands for explicit graph operations.
MCP server Claude CodeCodexCursor
DomainTome — the living knowledge graph for your software project. A programmatic MCP-backed graph of business logic, flows, events and rules. Runs locally from the domaintome Python package.
Agent
Read-only explorer for the DomainTome knowledge graph. Use when you need to scan many nodes, traverse the graph broadly, or summarize a subgraph without writing. Returns structured findings for the caller to act on. Never writes to DomainTome.
Command
Audit a DomainTome graph and report health (orphans, dangling edges, id hygiene, cycles). With no args, audits the active project. With a path, audits another project's graph without switching directory.
Command
Blast-radius analysis — what nodes are affected if this one changes?
Command
Initialize DomainTome for this project. Permanent alias for /dt:sync in INIT mode — both work, both are supported long-term.
Command
Show DomainTome nodes updated most recently. Use after a session to see what the graph captured.
Command
Detect drift between code and DomainTome — dead sourcerefs, stale nodes, never-verified nodes. Read-only.