Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- map_code_flow — Map the module graph you supply: render it as a Mermaid flowchart with cycles, orphans and dangling imports marked, and report entry points, leaves, hubs and dependency layers.
- find_structural_gaps — Find the structural gaps in the module graph you supply: orphan modules, the ring of every dependency cycle, the undocumented share, and edges pointing at undeclared modules.
- trace_consumers — Decide who has to be told about an interface change, from the interface and your own consumer inventory: each consumer's usage, whether notice is required, and what that rests on.
- analyse_impact — Score the blast radius of a change: classify every affected module by change type, breaking flag and consumer fan-in, and roll it into one 0-100 risk score whose weights are returned.
- suggest_regression_tests — Name the regression tests a change demands: contract, integration or unit per affected module, the evidence behind each, and the modules that genuinely need none.
- write_patch — Compose a line-accurate unified diff from the file contents and the edits you supply, refusing an anchor that is missing or ambiguous rather than guessing.
- plan_db_migration — Audit the migration DDL you paste for lock and downtime risk against Postgres or MySQL semantics, with a concrete safe rewrite. Advisory and read-only — it connects to no database.
- detect_n_plus_one — Read the slow-query log you paste: group it into query templates, flag the one-query-per-row N+1 signature, and suggest the indexes your catalog is missing.
- plan_legacy_migration — Turn a large migration's file list into a reviewable pull-request series of 20-40 independently mergeable files, with a per-file risk score and behaviour-equivalence flags.
- run_full — Run every capability you supplied the input for, in registry order, and return one report. Capabilities whose input is missing are listed as skipped.
- list_capabilities — List what this agent can do: every tool it advertises, what each one is for, and the arguments each one reads.
- plan_inputs — Plan the inputs for a tool: returns the questions to ask, the JSON schema of the arguments, and a ready-to-edit example.
- discover_intent — Understand your goal and co-design the exact input through clarifying questions before anything runs.
- open_form — Opens an interactive form that collects the run arguments. The form is the entry point for running the agent.
- run_form — Internal: invoked by the open_form form when the user submits. Not for direct use.
