evaluator

An autonomous checking workflow that compares a generator’s implementation with a written specification and uses Codex as a second reviewer when possible.

In plain words
What is it for?
Use it to verify completed code against a spec, report failures, and send structured feedback to the generator.
Why use it?
It provides an independent quality check and can keep reviewing work until it passes or needs user input.

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/flinedev/tandemkit/evaluator
Any agent
npx skills add FlineDev/TandemKit --skill evaluator
Clone the repo
git clone --depth 1 https://github.com/FlineDev/TandemKit

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,523 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 $0.00033 $0.07523
Opus 5 $0.00016 $0.03762
Sonnet 5 $0.00007 $0.01505
Haiku 4.5 $0.00003 $0.00752

Measured 2d ago against content hash 55dd33448926, 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.

skills/evaluator/SKILL.md · 409 lines

How it starts

The opening of the file, as written. The whole thing — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TandemKit — Evaluator

You are the Evaluator. Your job is to verify the Generator's work against the spec independently. You are not the Generator's friend — you are the quality gate. You work with Codex as a second opinion whenever possible. If Codex is temporarily unavailable (quota/timeout), you may proceed Claude-only for that round only — but permanent unavailability (auth failure) blocks the session.

This phase is fully autonomous. The user is NOT expected to be present. You and the Generator loop until PASS or the user intervenes.

UX Rules

  1. Use Variant 1 visual framing for copyable content.
  2. Report format is in templates/Evaluator-Round-Format.md. Strategies are in strategies/.
  3. Do NOT use subagents for evaluation — you and Codex are the two independent evaluators.

⛔ Signal Protocol — Atomic (NON-NEGOTIABLE) ⛔

A "signal" from the Evaluator to the Generator is NOT just a State.json write. It is a two-step atomic operation, and both steps must happen before your response ends. Skipping the second step deadlocks the loop — the Generator can flip to ready-for-eval in the next round but nothing will wake you to respond.

The same applies to the readiness signal at Step 2 (evaluatorStatus: watching) and to the "keep watching" watchers after every verdict.

The SIGNAL template — use this EVERY time you hand off or wait for a round

# Step 1 of 2 — Flip State.json (Edit/Write):
#   evaluatorStatus: "watching" | "evaluating" | "done"
#   verdict:         PASS / PASS_WITH_GAPS / FAIL / BLOCKED (after Step 4)
#   round:           N
#   updated:         <now>
#
# Step 2 of 2 — IMMEDIATELY launch the wake-up watcher in background.
#   Use the Bash tool with run_in_background: true. Do NOT foreground.
#   After a verdict, arm BOTH watchers (see Step 6: next-round + completion).
bash "$HOME/.claude/plugins/cache/FlineDev/tandemkit/latest/scripts/wait-for-state.sh" \
  "$(pwd)/TandemKit/<mission>" generatorStatus ready-for-eval

Read the full file on GitHub · 409 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 409 lines · 33 tokens per session scan A 55dd33448926

Subscribe to this mod's changes

evaluator is a skill published in the GitHub repository FlineDev/TandemKit (39 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 7,523 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 skills, from other repositories

crewai-multi-agent

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…

davila7/claude-code-templates · 61 tokens

build-monetized-app

Use when the task is building a new app on Eliza Cloud that earns money — chat apps, agent apps, MCP-backed tools, anything that calls the cloud's chat/messages/inference endpoints on behalf of users. Covers app registration, container deploy, markup configuration, affiliate header, app charge requests, x402 payment…

elizaOS/eliza · 126 tokens

contribute-to-eliza

Finish and prove a scoped elizaOS GitHub issue, or independently review and repair an open elizaOS pull request. Use when contributing compute to elizaOS by selecting unclaimed work, implementing or reviewing changes, adding real tests and evidence, validating artifacts, or preparing a contribution for maintainer…

elizaOS/eliza · 68 tokens

eliza-cloud

Use when the task involves Eliza Cloud or elizaOS Cloud as a managed backend, app platform, deployment target, billing layer, or monetization surface. The catch-all skill for any user request about THEIR existing apps / containers / earnings / credits / api-keys / analytics / billing / payment requests / payouts …

elizaOS/eliza · 191 tokens

discord

Use when you need to control Discord from Otto via the discord tool: send messages, react, post or upload stickers, upload emojis, run polls, manage threads/pins/search, create/edit/delete channels and categories, fetch permissions or member/role/channel info, set bot presence/activity, or handle moderation actions in…

elizaOS/eliza · 70 tokens

canvas

Display, present, and render HTML content on connected Otto nodes (Mac app, iOS, Android). Show on device, preview on mobile, push to screen, or navigate to a URL on any connected node. Use for games, visualizations, dashboards, interactive demos, and live-reloading development previews. Supports presenting, hiding…

elizaOS/eliza · 91 tokens