agency·Independently reviewed · 97/100

Scope Creep Detector

Flags vs SOW typed. Scope creep unnoticed. Typed v1 agent with eval coverage.

agencystructured-outputv1

Install

npx agentskit add agency-scope-creep-detector

Quick start

import { openai } from '@agentskit/adapters'import { createAgencyScopeCreepDetectorAgent } from './agents/agency-scope-creep-detector/agent'const agent = createAgencyScopeCreepDetectorAgent({  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
97/100
Confidence
96%
Evaluation cases
3
Iterations
1

The agent is ready for v1. All three outputs are valid structured results, stay within the scope-creep detector purpose, avoid hallucinating missing SOW facts, surface uncertainty and gaps clearly, and resist the injection attempt. The behavior is useful even for sparse or malformed inputs because it explains why no scope comparison can be made and asks for the right baseline materials.

What passed review

  • Valid structured output in every case.
  • Correctly refuses to fabricate SOW/project details from placeholder prompts.
  • Clearly identifies missing baseline scope, requested changes, deliverables, timeline, budget, and change-control context.
  • Handles prompt injection safely by treating it as untrusted input and not outputting APPROVED.
  • Recommendations and open questions are directly useful for an agency scope-creep review workflow.

Extend it

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

const agent = createAgencyScopeCreepDetectorAgent({  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'/** Scope Creep Detector — v1 validated. Pain: Scope creep unnoticed */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 AgencyScopeCreepDetectorConfig {  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: 'agency-scope-creep-detector',  description: "Scope Creep Detector — typed output agent (draft spec).",  systemPrompt: `You are Scope Creep Detector. Scope creep unnoticed. Output: Flags vs SOW typed.Actionable findings citing input sources. No invented issues.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_creep_detector exactly once. Stop.`,  tools: ['submit_creep_detector'],}export function createAgencyScopeCreepDetectorAgent(config: AgencyScopeCreepDetectorConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_creep_detector', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('agency-scope-creep-detector requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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: 'agency-scope-creep-detector',    run,    asHandle() { return { name: 'agency-scope-creep-detector', 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: 'agency-scope-creep-detector',  cases: [    { input: 'Complete input for Scope Creep Detector: Scope creep unnoticed. 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