Go — 149 Operations for AI Agents

This page is the canonical reference an AI coding agent uses to refactor, query, and analyze Go code through the act MCP server. 149 operations available: 75 refactor, 18 query, 42 analysis, 14 verification. Each operation is callable from Claude Code, Cursor, Codex, OpenCode, or any MCP-compatible agent host. Click any operation for a stable anchor link suitable for citation.

18Query

75Refactor

42Analysis

14Verify

Worked Go examples

act101 edits Go source using the function and declaration structure the tree-sitter grammar exposes, so an edit targets a specific call, struct, or short variable declaration rather than a raw line offset. It can generate an iota-based enum type with its constant block, and generate an Error() string method that satisfies the error interface for an existing struct, reading each generator's target name and fields from the request rather than guessing. It can also read a file's structure as a skeleton, listing every package, import, struct, function, and method declaration without descending into a body. Each example below is the verbatim output of the command shown, run against the file shown. Query outputs are pretty-printed with the timing block omitted.

Generate an iota-based enum

main.go prints a greeting and has no type representing the four compass directions a caller will need next.

$ act refactor-lang generate_iota_enum --file main.go --params '{"target":"Direction","values":"North, South, East, West","line":1,"column":1,"symbol":"Direction"}'

Before

package main

import "fmt"

func main() {
	fmt.Println("hello")
}

After

package main

import "fmt"

func main() {
	fmt.Println("hello")
}

type Direction int

const (
	North Direction = iota
	South
	East
	West
)

A Direction type and a const block using iota are appended, giving North the value 0 and incrementing South, East, and West from it.

Generate an Error() method for a custom error type

errors.go defines CustomError with a Message field but does not yet satisfy Go's error interface.

$ act refactor-lang generate_error_method_go --file errors.go --params '{"type_name":"CustomError","message_field":"Message","line":6,"column":6,"symbol":"CustomError"}'

Before

package main

type CustomError struct {
	Message string
}

After

package main

type CustomError struct {
	Message string
}

func (c CustomError) Error() string {
	return c.Message
}

An Error() string method is appended that returns c.Message, so CustomError now satisfies the standard library error interface.

Read the file's structure without bodies

limiter.go declares the Limiter struct with three fields, a NewLimiter constructor function, and two methods, Allow and Reset.

$ act query skeleton limiter.go

Before

package ratelimit

import "time"

// Limiter enforces a maximum number of requests per interval.
type Limiter struct {
	max      int
	interval time.Duration
	tokens   int
}

func NewLimiter(max int, interval time.Duration) *Limiter {
	return &Limiter{max: max, interval: interval, tokens: max}
}

func (l *Limiter) Allow() bool {
	if l.tokens <= 0 {
		return false
	}
	l.tokens--
	return true
}

func (l *Limiter) Reset() {
	l.tokens = l.max
}

Output

{
    "type": "Skeleton",
    "declarations": [
        {
            "kind": "package",
            "name": "ratelimit",
            "range": {
                "start": {
                    "file": "limiter.go",
                    "line": 1,
                    "column": 1,
                    "byte_offset": 0
                },
                "end": {
                    "file": "limiter.go",
                    "line": 1,
                    "column": 18,
                    "byte_offset": 17
                }
            },
            "name_range": {
                "start": {
                    "file": "limiter.go",
                    "line": 1,
                    "column": 9,
                    "byte_offset": 8
                },
                "end": {
                    "file": "limiter.go",
                    "line": 1,
                    "column": 18,
                    "byte_offset": 17
                }
            }
        },
        {
            "kind": "import",
            "name": "import \"time\"",
            "range": {
                "start": {
                    "file": "limiter.go",
                    "line": 3,
                    "column": 1,
                    "byte_offset": 19
                },
                "end": {
                    "file": "limiter.go",
                    "line": 3,
                    "column": 14,
                    "byte_offset": 32
                }
            }
        },
        {
            "kind": "struct",
            "name": "Limiter",
            "range": {
                "start": {
                    "file": "limiter.go",
                    "line": 6,
                    "column": 6,
                    "byte_offset": 102
                },
                "end": {
                    "file": "limiter.go",
                    "line": 10,
                    "column": 2,
                    "byte_offset": 172
                }
            },
            "name_range": {
                "start": {
                    "file": "limiter.go",
                    "line": 6,
                    "column": 6,
                    "byte_offset": 102
                },
                "end": {
                    "file": "limiter.go",
                    "line": 6,
                    "column": 13,
                    "byte_offset": 109
                }
            }
        },
        {
            "kind": "function",
            "name": "NewLimiter",
            "range": {
                "start": {
                    "file": "limiter.go",
                    "line": 12,
                    "column": 1,
                    "byte_offset": 174
                },
                "end": {
                    "file": "limiter.go",
                    "line": 14,
                    "column": 2,
                    "byte_offset": 295
                }
            },
            "name_range": {
                "start": {
                    "file": "limiter.go",
                    "line": 12,
                    "column": 6,
                    "byte_offset": 179
                },
                "end": {
                    "file": "limiter.go",
                    "line": 12,
                    "column": 16,
                    "byte_offset": 189
                }
            }
        },
        {
            "kind": "method",
            "name": "Allow",
            "range": {
                "start": {
                    "file": "limiter.go",
                    "line": 16,
                    "column": 1,
                    "byte_offset": 297
                },
                "end": {
                    "file": "limiter.go",
                    "line": 22,
                    "column": 2,
                    "byte_offset": 394
                }
            },
            "name_range": {
                "start": {
                    "file": "limiter.go",
                    "line": 16,
                    "column": 19,
                    "byte_offset": 315
                },
                "end": {
                    "file": "limiter.go",
                    "line": 16,
                    "column": 24,
                    "byte_offset": 320
                }
            }
        },
        {
            "kind": "method",
            "name": "Reset",
            "range": {
                "start": {
                    "file": "limiter.go",
                    "line": 24,
                    "column": 1,
                    "byte_offset": 396
                },
                "end": {
                    "file": "limiter.go",
                    "line": 26,
                    "column": 2,
                    "byte_offset": 443
                }
            },
            "name_range": {
                "start": {
                    "file": "limiter.go",
                    "line": 24,
                    "column": 19,
                    "byte_offset": 414
                },
                "end": {
                    "file": "limiter.go",
                    "line": 24,
                    "column": 24,
                    "byte_offset": 419
                }
            }
        }
    ]
}

The skeleton lists Limiter as kind struct, NewLimiter as kind function, and Allow/Reset as kind method, alongside the package and import declarations — six declarations total, none of them showing a method body.

Query

18 query tools, the same on every supported language. Descriptions live in the shared reference: /docs/query-tools.

callers control_flow data_flow definition diagnostics effect_closure effect_summary fix_auto get_type graph import_organize interface mutations references repo_outline skeleton symbols symbols_batch

Refactor

Operation	Description
`add-context-parameter`	Add a context.Context parameter to a function
`add-defer-statement`	Add defer statement for resource cleanup
`add-error-handling`	Wrap function call with if err != nil error handling
`add-nil-check-for-interface`	Add nil check before calling a method on an interface value
`add-type-assertion-guard`	Wrap type assertion with comma-ok idiom to prevent panic
`add-underscore-blank-identifier`	Convert unused return value to blank identifier _
`change-receiver`	Change a method's receiver type
`change-signature`	Change function/method signature
`change-type`	Change symbol type annotation
`change-visibility`	Change symbol visibility
`combine`	Combine related declarations
`delete`	Delete symbol and update references
`encapsulate`	Encapsulate field with accessors
`extract-class`	Extract methods/fields to new type
`extract-constant`	Extract value to named constant
`extract-enum-member`	Extract enum member value
`extract-function`	Extract code into a new function
`extract-interface`	Extract interface from implementation
`extract-type`	Extract inline type into named type
`extract-variable`	Extract expression to variable
`extract_function`	Extract a code selection into a new function — automatically infers parameters, return types, and inserts the call site. Use instead of manually cutting/pasting code. Works without LSP; LSP improves type inference. Params: file (string), new_name (string), start_line (u32), start_column (u32), end_line (u32), end_column (u32) [, preview (bool), receipt (bool)]
`extract_variable`	Extract an expression into a named variable — inserts the declaration and replaces the expression with the variable name. Works without LSP. Params: file (string), new_name (string), start_line (u32), start_column (u32), end_line (u32), end_column (u32) [, preview (bool)]
`flatten`	Flatten nested structure
`generate-accessors`	Generate getters/setters for fields
`generate-builder`	Generate builder pattern implementation
`generate-constructor`	Generate constructor from fields
`generate-constructor-function`	Generate a Go constructor function (New<Type>)
`generate-documentation-comment`	Generate documentation comment
`generate-equality-method`	Generate Equal() method with field comparisons
`generate-equals`	Generate equality implementation
`generate-error-method`	Generate Error() method (error interface)
`generate-error-type`	Generate custom error struct with Error() method
`generate-from-json`	Generate JSON deserialization code
`generate-getters-setters`	Generate getter and setter methods
`generate-hash`	Generate hash implementation
`generate-impl`	Generate implementation from interface
`generate-interface-implementation`	Generate interface implementation stubs
`generate-iota-enum`	Generate enum type using iota constant generator
`generate-mapped-type`	Generate mapped/projection type
`generate-struct-stringer`	Generate String() method for struct (fmt.Stringer)
`generate-table-driven-test`	Generate table-driven test pattern
`generate-test-file`	Generate test file scaffold
`generate-tests`	Generate unit test skeletons
`generate-to-json`	Generate JSON serialization code
`generate-to-string`	Generate string conversion implementation
`generate-type-guard`	Generate type-check helper
`import-add`	Add missing import declaration
`import-alias`	Add alias to import declaration
`import-organize`	Organize/sort imports
`import-remove`	Remove unused import declaration
`inline`	Inline a variable, function, or method — replace every usage with its definition body, then remove the original. The inverse of extract. Works without LSP (single-file); LSP enables cross-file inlining. Params: file (string), symbol (string) [, line (u32), preview (bool), receipt (bool)]
`inline`	Inline symbol at all usage sites
`insert_body`	Replace a function's implementation body with new code. AST-validated — rejects if the result has parse errors, so you can't accidentally break syntax. Use instead of manual text editing for function rewrites. Params: file (string), symbol (string), code (string) [, commit (bool)]
`introduce-field`	Introduce new field in type
`introduce-parameter`	Introduce parameter in signature
`introduce-variable`	Introduce variable for expression
`move`	Move symbol to another file/package
`move_symbol`	Move a function, class, or type to a different file and automatically update all imports across the codebase. Use instead of manually cut/paste + fixing imports. Works without LSP (single-file); LSP enables cross-file import updates. Params: file (string), symbol (string), destination (string) [, preview (bool), receipt (bool)]
`pull-up`	Pull member up hierarchy
`push-down`	Push member down hierarchy
`recipe_run`	Run a codemod recipe: declarative match → transform → optional verify across modeled grammars. Preview lists matches; apply writes with optional E7 receipts and all-or-nothing rollback. Returns a per-site report.
`remove-error-assignment`	Convert blank error assignment to named variable
`rename`	Rename a symbol and automatically update ALL references across the codebase. Safer and faster than find-and-replace — AST-aware, won't rename strings or comments. Works without LSP (single-file); LSP enables cross-file renames. Params: file (string), old_name (string), new_name (string) [, line (u32), column (u32), preview (bool), receipt (bool)]
`rename`	Rename symbol and all references
`split`	Split large declaration into smaller parts
`wrap-defer`	Wrap selected code in a defer statement
`wrap-error`	Wrap selected code in error handling
`wrap-error-check`	Wrap selected code in error check pattern
`wrap-goroutine`	Wrap selected code in a goroutine
`wrap-if`	Wrap code in conditional
`wrap-lock`	Wrap critical section with lock
`wrap-null-check`	Wrap code with nil guard
`wrap-optional`	Wrap value in Optional
`wrap-try-catch`	Wrap code in try/catch equivalent
`wrap-using`	Wrap resource usage in scope guard

Analysis

42 analysis tools, the same on every supported language. Descriptions live in the shared reference: /docs/analysis-tools.

analyze_api_diff analyze_chokepoints analyze_clones analyze_clusters analyze_cohesion analyze_conformance analyze_coupling analyze_cycle_risk analyze_cycles analyze_dead_code analyze_depth analyze_entry_points analyze_export analyze_extraction analyze_fan_balance analyze_features analyze_hotspots analyze_impact analyze_inconsistencies analyze_inheritance analyze_interface_bloat analyze_interfaces analyze_layers analyze_orphan_types analyze_patterns analyze_platform_deps analyze_readiness analyze_roles analyze_seams analyze_stability analyze_surface analyze_test_gaps analyze_thickness analyze_type_completeness churn_hotspots co_change_clusters coverage_overlay ownership_map profile_overlay simulate split_module trace_overlay

Verify

14 verify tools, the same on every supported language. Descriptions live in the shared reference: /docs/verification.

bisect_regression gate generate_test_harness scan secret_surface summarize_pr taint_flow unsafe_surface verify_behavioral_equivalence verify_contract_preserved verify_diff_semantics verify_port_parity verify_side_effects verify_test_impact

← GNGo Modules →