adev:eval

A quality-testing workflow that scores an implementation from 0 to 100 across automated checks, system design, an AI review, and human review.

In plain words
What is it for?
Use it to evaluate a particular specification, run one evaluation layer, configure the scoring process, or apply a custom review rubric.
Why use it?
A single pass-or-fail result can hide differences in implementation quality. This workflow provides separate evaluation layers and requires the project’s validation setup before running.

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/agentic-development/adev-plugin/eval
Any agent
npx skills add agentic-development/adev-plugin --skill eval
Clone the repo
git clone --depth 1 https://github.com/agentic-development/adev-plugin

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,593 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 $0.00047 $0.04593
Opus 5 $0.00023 $0.02296
Sonnet 5 $0.00009 $0.00919
Haiku 4.5 $0.00005 $0.00459

Measured 2d ago against content hash 2d38ff9342fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adev:eval 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.

providers/codex/skills/eval/SKILL.md · 308 lines

How it starts

The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Graduated Evaluation Harness

Score implementation quality across four evaluation layers, producing a graduated quality score (0-100) rather than a single binary pass/fail. Complements /adev:validate with nuanced quality assessment.

Layer 3 is the exception to "graduated": its judged output is a table of per-criterion binary verdicts, aggregated into points only so the total stays comparable across runs. See Layer 3 for why.

Announce at start: "I'm using the adev:eval skill to run the evaluation harness."

Arguments

  • --spec <path>: evaluate the implementation of a specific spec (required)
  • --layer <N>: run only a specific layer (1-4)
  • --configure: interactive setup of eval configuration
  • --rubric <path>: use a custom rubric for Layer 3, overriding the default. The file must carry the same top-level keys as the default rubric (see Layer 3).
  • --no-infra: skip infrastructure preflight checks (user-only — the agent must never set this flag)

Prerequisites

  1. .context-index/ must be initialized.
  2. /adev:validate should have passed (eval builds on top of validation, not replaces it).
  3. For Layer 2, .context-index/samples/ should have relevant golden samples.
  4. Eval configuration lives in .context-index/evals/config.yaml (generated by --configure).

Preflight: Infrastructure Verification

After verifying prerequisites, check whether the spec declares infra_requirements. If so, run the infrastructure preflight before proceeding to evaluation layers.

Layer-aware skip: If --layer 1 or --layer 2 is specified, skip the preflight step (no code execution against external systems in those layers).

--no-infra resolution: Read --no-infra flag from arguments. If not passed, check ADEV_NO_INFRA env var (only exact value 1 activates bypass). Read once at skill entry, convert to options.noInfra. The agent must never set --no-infra or ADEV_NO_INFRA autonomously — if preflight fails, report the failure and wait for user direction.

Read the full file on GitHub · 308 lines

Files

What ships with it

1 file 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 · 308 lines · 47 tokens per session scan A 2d38ff9342fb

Subscribe to this mod's changes

adev:eval is a skill published in the GitHub repository agentic-development/adev-plugin (11 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 4,593 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens