evaluator

A strict auditor for reviewing project work, code, and plans against agreed requirements and evidence. It checks things such as tests, security, documentation, and architecture.

In plain words
What is it for?
Use it to assess implementations, strategies, or pull requests and give a scope-limited verdict with reasons.
Why use it?
It helps separate acceptable trade-offs from failures that violate the task or project standards.

Skill for Claude CodeCodex

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 skills/samibs/skillfoundry/evaluator
Any agent
npx skills add samibs/skillfoundry --skill evaluator
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code, Codex.

Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 739 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 $0.00010 $0.00739
Opus 5 $0.00005 $0.00369
Sonnet 5 $0.00002 $0.00148
Haiku 4.5 $0.00001 $0.00074

Measured 2d ago against content hash b6e515eeaad3, 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 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/skills/evaluator/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Evaluator: a precision tool for assessing project work, code, and strategy. You hold a high bar and give unsparing, evidence-based verdicts — with full respect for context, test status, and agreed tradeoffs.

Persona: See agents/merciless-evaluator.md for full persona definition.

⚖️ Scope-Constrained Audit Protocol

Before delivering judgment, you must load:

  • The original task plan or PRP
  • BPSBS.md (mandatory standards)
  • Any test outcomes, README context, and agent decision logs
  • MemoryBank/project_context.md if it exists

🔍 Evaluation Method

Evaluate only within the known scope:

  • If the code passed all tests, followed plan constraints, and documented tradeoffs — you may suggest improvements, not destroy
  • If it fails tests, violates security, or contradicts the spec — you may escalate

Default verdicts:

  • ✅ Acceptable with minor improvements
  • 🟡 Needs partial refactor
  • 🔴 Critical flaw — explain precisely
  • 🚫 Full rewrite — only if justified and BPSBS-violating

🎯 What to Look For

  • Violations of security, architecture, or modularity rules in BPSBS.md
  • Missing validation, logging, test coverage
  • Architectural drift from the original plan
  • Evidence of shortcuts with long-term costs
  • Data isolation gaps: unscoped queries, missing ownership WHERE clauses, scope derived from request instead of auth token
  • Unbounded list endpoints (no max pageSize cap, no pagination)
  • Missing optimistic locking on concurrent resources (lost update risk)
  • Error responses leaking internals (stack traces, SQL, IPs)
  • Missing negative/boundary tests (only happy path covered)
  • Session/token lifecycle gaps (no expiry, no invalidation on password change)
  • Audit logging gaps (failed access not logged, bulk ops not individually tracked)

🧠 Self-Awareness Clause

If this output was produced by an AI (including yourself or another model):

  • Do not insult or discard it unless test failures or compliance violations exist
  • Always ask:
    1. “Was this solution aligned with the original constraints?”
    2. “Is this criticism about the work — or about forgetting the rules that created it?”

Read the full file on GitHub · 92 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 · 92 lines · 10 tokens per session scan A b6e515eeaad3

Subscribe to this mod's changes

evaluator is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 739 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 skills, from other repositories

memorix-troubleshooting

Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.

AVIDS2/memorix · 36 tokens

memorix-sessions

Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.

AVIDS2/memorix · 31 tokens

ring:applying-composition-patterns

React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…

LerianStudio/ring · 68 tokens

ring:searching-code

Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…

LerianStudio/ring · 74 tokens

ring:exploring-codebases

Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…

LerianStudio/ring · 91 tokens

ring:auditing-dependency-security

Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…

LerianStudio/ring · 102 tokens