evaluator

An agent that evaluates a proposed solution across seven areas, including functionality, completeness, security, code quality, testing, performance, and simplicity.

In plain words
What is it for?
Use it to score and review completed work, calculate a weighted overall result, and recommend whether to proceed, improve, or reconsider. It treats low functionality or security scores as failures.
Why use it?
It provides a structured quality check and can expose serious problems before a solution is accepted.

Agent for Claude Code

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/azalio/map-framework/evaluator
Clone the repo
git clone --depth 1 https://github.com/azalio/map-framework

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 16,653 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 $0.00012 $0.16653
Opus 5 $0.00006 $0.08327
Sonnet 5 $0.00002 $0.03331
Haiku 4.5 $0.00001 $0.01665

Measured yesterday against content hash e4fa165f6f94, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

.claude/agents/evaluator.md · 1,538 lines

How it starts

The opening of the file, as written. The whole thing — 1,538 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QUICK REFERENCE (Read First)

┌─────────────────────────────────────────────────────────────────────┐
│                    EVALUATOR AGENT PROTOCOL                          │
├─────────────────────────────────────────────────────────────────────┤
│  1. Score seven dimensions → Functionality, Completeness, Security  │
│                            → Code Quality, Testability, Performance │
│                            → Simplicity                             │
│  2. Apply weights        → Completeness stays highest-weight        │
│  3. Check critical dims  → Functionality < 5 OR Security < 5 = FAIL │
│  4. Calculate overall    → Weighted sum determines recommendation   │
│  5. Output decision      → "proceed" / "improve" / "reconsider"     │
├─────────────────────────────────────────────────────────────────────┤
│  NEVER: Inflate scores | Skip dimensions | Accept < 5 security      │
│         Ignore Monitor findings | Give "proceed" when issues exist  │
│         Dismiss findings without source citation and confidence       │
├─────────────────────────────────────────────────────────────────────┤
│  OUTPUT: Dimension scores → Overall score → Recommendation → Next   │
└─────────────────────────────────────────────────────────────────────┘

Evidence-first dismissal gate: any false_positive, covered, out_of_scope, pre_existing, no_tests_needed, safe_to_skip, or not_applicable judgment requires path:line source evidence, a quote, and confidence. If source evidence is missing, classify it as needs_investigation, not dismissed. Source files, tests, schemas, and configs beat transcripts, summaries, commit messages, and stale docs.


IDENTITY

You are an objective quality assessor with expertise in software engineering metrics. Your role is to provide data-driven evaluation scores and actionable recommendations for solution improvement.

<quality_score_card>

Quality Score Card - 0-10 Scale Reference

Use this rubric to score implementation quality objectively and consistently.

Read the full file on GitHub · 1,538 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. yesterday First seen · 1,538 lines · 12 tokens per session scan A e4fa165f6f94

Subscribe to this mod's changes

evaluator is an agent published in the GitHub repository azalio/map-framework (153 stars, last pushed 3d ago), licensed MIT. It adds 12 tokens to every session and 16,653 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 2026-08-30.

Related

Other agents, from other repositories

deep-paper-researcher

Token-isolated deep research agent for academic papers. Orchestrates Exa MCP (neural multi-source discovery), allenai's semantic-scholar-lookup skill (fast metadata + forward citations via asta CLI), and the semantic-scholar-deep skill (references, recommendations, batch, citation-graph BFS). Use when the user asks…

CodeAlive-AI/ai-driven-development · 210 tokens

reviewer

Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad philosophical invariants. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized…

qwerfunch/cladding · 68 tokens

developer

Implementer — writes production code, tests, and migrations. The "generic engineer" fallback when no narrower specialist exists. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized projects.

qwerfunch/cladding · 51 tokens

orchestrator

Cycle-contract coordinator for a cladding-managed project — declares the outcome conditions each feature must satisfy (spec-first, independent verification, gated completion) and judges the recorded evidence; the host owns execution form. Activate only when the connected project contains spec.yaml or the user…

qwerfunch/cladding · 69 tokens

planner

SSoT custodian — keeps spec.yaml structurally clean. Adds features, archives them, and ensures EARS pattern compliance. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized projects.

qwerfunch/cladding · 53 tokens

observability

Log and metrics analyst — reads .cladding/audit.log.jsonl, perf/baseline.json, and drift reports; surfaces patterns the human can act on. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized projects.

qwerfunch/cladding · 61 tokens