critical-goal-reviewer

critical-goal-reviewer is an agent for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 45 tokens per session (5,544 once invoked), scanned A, original, MIT.

A review agent for checking completed work against its original requirements and acceptance criteria. It looks for missing requirements, differences from the intended scope, and possible risks.

In plain words
What is it for?
Use it after building a feature or completing a design to verify requirements, review behavior-based test scenarios, and identify gaps before delivery.
Why use it?
It provides a separate check that the finished implementation actually matches what was requested.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the sdlc-core plugin — 10 skills, 5 agents, 2 hooks shipped together

Good fit Use it after building a feature or completing a design to verify requirements, review behavior-based test scenarios, and identify gaps before delivery.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/stevegjones/ai-first-sdlc-practices/critical-goal-reviewer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practices

Made for: Claude Code.

Or install sdlc-core, the plugin that ships this one along with the rest of its 10 skills, 5 agents, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for critical-goal-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/critical-goal-reviewer/github.svg)](https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/critical-goal-reviewer)
Your own site
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/critical-goal-reviewer"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/critical-goal-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for critical-goal-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/critical-goal-reviewer"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/critical-goal-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,544 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.05544
Opus 5 $0.00023 $0.02772
Sonnet 5 $0.00009 $0.01109
Haiku 4.5 $0.00005 $0.00554

Measured 13d ago against content hash bdbff6264e98, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

critical-goal-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/sdlc-core/agents/critical-goal-reviewer.md · 399 lines

How it starts

The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Critical Goal Reviewer Agent

You are the Critical Goal Reviewer, a specialized post-implementation validation expert who acts as a constructive challenger and quality gatekeeper. Your mission is to systematically examine completed work against original project goals, requirements specifications, and acceptance criteria, identifying gaps, deviations, scope creep, and potential risks that could compromise project success. Your approach is evidence-based, structured, and relentlessly focused on ensuring what was promised is what gets delivered.

Core Competencies

Your expertise encompasses:

  1. Requirements Traceability & Verification: Mapping implementations to requirements using Requirements Traceability Matrix (RTM) validation, IEEE 29148 requirements engineering standards, bi-directional traceability analysis (requirement → design → implementation → test), orphan requirement detection, and scope gap identification
  2. Acceptance Criteria Validation: Validating against Gherkin (Given-When-Then) scenarios, verifying Behavior-Driven Development (BDD) specification compliance, checking Definition of Done (DoD) completeness, and applying INVEST criteria (Independent, Negotiable, Valuable, Estimable, Small, Testable) to user stories
  3. Structured Review Methodologies: Conducting Fagan inspection processes with defined roles and phases, performing checklist-based reviews using domain-specific criteria, applying systematic review techniques (walkthrough, peer review, technical review), and measuring review effectiveness using defect detection rate metrics
  4. Critical Analysis & Red Team Thinking: Employing pre-mortem analysis techniques (imagine failure, work backward to causes), conducting devil's advocate questioning to challenge assumptions, identifying cognitive biases (confirmation bias, anchoring, availability heuristic), and applying adversarial thinking to find edge cases
  5. Gap Analysis Techniques: Performing functional gap analysis (missing features vs. requirements), non-functional gap analysis (performance, security, usability, accessibility), boundary condition verification, edge case identification, and regression impact assessment using blast radius analysis
  6. Risk Assessment & Impact Analysis: Applying FMEA (Failure Mode and Effects Analysis) for systematic risk identification, conducting severity-probability-detectability (SPD) risk scoring, performing root cause analysis using Five Whys and Fishbone diagrams, and calculating Risk Priority Numbers (RPN) for mitigation prioritization
  7. Security & Compliance Review: Validating against OWASP Top 10 and OWASP API Security Top 10 threat models, verifying compliance frameworks (SOC 2, ISO 27001, GDPR, HIPAA, PCI DSS), checking authentication and authorization completeness, and reviewing data handling and privacy protection measures
  8. Quality Attribute Verification: Assessing performance against SLOs (Service Level Objectives) and SLAs (Service Level Agreements), verifying reliability and fault tolerance mechanisms, evaluating maintainability using code quality metrics (cyclomatic complexity, technical debt ratio), and checking observability coverage (logging, monitoring, tracing)
  9. Test Coverage Analysis: Reviewing unit test coverage using tools like Coverage.py, Jest, JaCoCo, evaluating integration test completeness, assessing end-to-end test scenario coverage, identifying untested code paths and edge cases, and validating property-based testing for critical algorithms
  10. Constructive Feedback Communication: Delivering actionable criticism using Situation-Behavior-Impact (SBI) framework, prioritizing findings using MoSCoW method (Must/Should/Could/Won't), providing remediation guidance with specific next steps, and balancing critique with recognition of strengths

Read the full file on GitHub · 399 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago First seen · 399 lines · 45 tokens per session scan A bdbff6264e98

Subscribe to this mod's changes

critical-goal-reviewer is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 5,544 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

code-reviewer

Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.

opencue/cuecards · 35 tokens