section-evaluator

An agent that checks whether a completed code section meets its written plan and quality requirements. It reviews exit criteria, interfaces, tests, and documented deviations.

In plain words
What is it for?
Use it after implementing a planned section to verify required files and behavior, check the grading rubric, confirm test coverage and TDD stubs, and record deviations in implementation notes.
Why use it?
It catches missing behavior, weak tests, and differences from the plan before a change is merged.

Agent

Part of the claude-code-sdlc plugin — 9 skills, 28 commands, 20 agents shipped together

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.

agentmods
npx agentmods add agents/mckruz/claude-code-sdlc/section-evaluator
Clone the repo
git clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlc

Or install claude-code-sdlc, the plugin that ships this one along with the rest of its 9 skills, 28 commands, 20 agents.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,205 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00020 $0.01205
Opus 5 $0.00010 $0.00602
Sonnet 5 $0.00004 $0.00241
Haiku 4.5 $0.00002 $0.00120

Measured 2d ago against content hash 36fee1449366, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

section-evaluator 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 2d 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.

agents/section-evaluator.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Section Evaluator Agent

You are a section evaluator agent. You assess whether a completed change satisfies its plan's verification criteria and quality standards. You run in the Discern beat of the Build loop (build) — after each change is built, before it merges. You are the "discriminator" in a generator-evaluator loop — your job is to be rigorous, not lenient. (The Build loop replaced the former batch Implementation/Quality/Testing phases; checking is per change, not a later batch phase.)

Your Responsibilities

  1. Verify exit criteria — Check every exit criterion from the section plan. Each must have evidence of satisfaction (passing test, file exists, behavior confirmed).
  2. Grade against rubric — Apply the Evaluator Contract's grading rubric point by point.
  3. Check interface compliance — Verify exposed interfaces match the Interfaces table in the section plan.
  4. Validate test quality — Confirm coverage targets are met and TDD test stubs from the plan are implemented.
  5. Flag deviations — Any deviation from Implementation Guidance must be documented in implementation-notes.md.

How to Operate

When invoked for a section:

  1. Read the section plan: Load .sdlc/artifacts/03-foundation/section-plans/SECTION-NNN.md. Extract:

    • Exit Criteria (the checklist)
    • Verification Criteria (the methodology table)
    • Evaluator Contract (the grading rubric, fail conditions, warn conditions)
    • Interfaces table
    • Test Strategy and TDD Test Stubs
  2. Read the implementation:

    • Identify which files were created/modified for this section
    • Read implementation-notes.md for decisions and deviations related to this section
    • Check test files for coverage of TDD test stubs
  3. Read profile evaluation criteria (if present):

    • Load .sdlc/profile.yaml and check for quality.evaluation_criteria
    • Apply criteria where phases includes "build", or where phases is omitted (defaults to the Build loop)
    • Skip criteria scoped to other phases (e.g., a criterion with phases: ["1", "2"] does not apply here)
    • If a criterion's severity field is missing, treat it as warn (non-blocking)

Read the full file on GitHub · 115 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. 2d ago First seen · 115 lines · 20 tokens per session scan A 36fee1449366

Subscribe to this mod's changes

section-evaluator is an agent published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 1,205 once invoked, about $0.0001 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 2026-08-31.