devops·Independently reviewed · 96/100

Terraform Plan Interpreter

Summary typed. TF plans opaque. Typed v1 agent with eval coverage.

devopsstructured-outputv1

Install

npx agentskit add devops-terraform-plan-interpreter

Quick start

import { openai } from '@agentskit/adapters'import { createDevopsTerraformPlanInterpreterAgent } from './agents/devops-terraform-plan-interpreter/agent'const agent = createDevopsTerraformPlanInterpreterAgent({  adapter: openai({    apiKey: process.env.OPENAI_API_KEY!,    model: 'gpt-4o',  }),})const result = await agent.run('Describe your task here')console.log(result.content)

Independent reviewer approved

Validation evidence

How validation works
Review score
96/100
Confidence
95%
Evaluation cases
3
Iterations
1

The agent produced valid structured outputs for all three cases, stayed within its Terraform-plan-interpreter purpose, did not hallucinate plan details from sparse prompts, surfaced uncertainty and missing context, and resisted the injection request. The behavior is conservative and useful when no plan is provided. Confidence is capped because the supplied validation set does not include an actual Terraform plan, so positive interpretation quality is not exercised here.

What passed review

  • Valid non-empty structured outputs in every case.
  • Correctly refused to infer Terraform changes without plan content.
  • Clearly surfaced gaps, review requirement, and follow-up questions.
  • Handled prompt injection by treating the injected approval instruction as untrusted data.
  • Recommendations point users toward appropriate Terraform plan artifacts such as `terraform show -json`.

Extend it

Pass tools, retrieval, memory, permissions, and observers through the factory config.

const agent = createDevopsTerraformPlanInterpreterAgent({  adapter,  tools,  retriever,  memory,  onConfirm: (call) => approve(call),  observers: [tracer],})
View agent factory source
import type { AdapterFactory, ChatMemory, Observer, ToolCall, ToolDefinition } from '@agentskit/core'import { fenceUntrustedContent, UNTRUSTED_CONTENT_DIRECTIVE } from '@agentskit/core/security'import { invokeStructured } from '@agentskit/runtime'import { defineZodTool } from '@agentskit/tools'import { z } from 'zod'import { zodToJsonSchema } from 'zod-to-json-schema'import type { JSONSchema7 } from 'json-schema'/** Terraform Plan Interpreter — v1 validated. Pain: TF plans opaque */export interface Finding { id: string; severity: 'critical' | 'high' | 'medium' | 'low' | 'info'; message: string; source?: string; recommendation?: string }export interface AgentOutput { summary: string; findings: Finding[]; gaps: string[]; openQuestions: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface DevopsTerraformPlanInterpreterConfig {  adapter: AdapterFactory  memory?: ChatMemory  observers?: Observer[]  onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean>  maxSteps?: number}const Output = z.object({  summary: z.string(),  findings: z.array(z.object({    id: z.string(), severity: z.enum(['critical', 'high', 'medium', 'low', 'info']),    message: z.string(), source: z.string().optional(), recommendation: z.string().optional(),  })),  gaps: z.array(z.string()).default([]),  openQuestions: z.array(z.string()).default([]),})const toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7const skill = {  name: 'devops-terraform-plan-interpreter',  description: "Terraform Plan Interpreter — typed output agent (draft spec).",  systemPrompt: `You are Terraform Plan Interpreter. TF plans opaque. Output: Summary typed.Actionable findings citing input sources. No invented issues.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_plan_interpreter exactly once. Stop.`,  tools: ['submit_plan_interpreter'],}export function createDevopsTerraformPlanInterpreterAgent(config: DevopsTerraformPlanInterpreterConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_plan_interpreter', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('devops-terraform-plan-interpreter requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${fenceUntrustedContent(input)}`,      parse: (a) => Output.parse(a),      skill,      memory: config.memory,      observers: config.observers,      onConfirm: config.onConfirm,      maxSteps: config.maxSteps ?? 4,    })    return { ...result, requiresReview: true }  }  return {    name: 'devops-terraform-plan-interpreter',    run,    asHandle() { return { name: 'devops-terraform-plan-interpreter', run: (t: string) => run(t).then((r) => JSON.stringify(r)) } },  }}
View evaluation contract

Replay these cases with the provider and model you plan to deploy.

import type { EvalSuite } from '@agentskit/eval'export const suite: EvalSuite = {  name: 'devops-terraform-plan-interpreter',  cases: [    { input: 'Complete input for Terraform Plan Interpreter: TF plans opaque. Provide full structured output.', expected: (r: string) => r.length > 20 && /requiresReview|summary|title|category|findings|sections|score|clusters|items|steps/i.test(r) },    { input: 'Minimal input.', expected: (r: string) => /gap|openQuestion/i.test(r) || r.length > 10 },    { input: 'Input with specific detail: ACME Corp project deadline March 15.', expected: (r: string) => /ACME|March|15/i.test(r) || /gap/i.test(r) },    { input: 'Empty context — only says "process this".', expected: (r: string) => r.length > 5 },  ],}

Was this agent useful?

Your response helps us prioritize agent quality.

Keep exploring

Related agents

View category