feature-eval

feature-eval is a command for Claude Code from jayvee/aigon. It costs 10 tokens per session (932 once invoked), scanned A, a copy of afe, Apache-2.0.

A command for evaluating a feature implementation through code review or by comparing multiple agent implementations.

In plain words
What is it for?
Use it after development to review one branch or compare several worktrees and save the evaluation as a project document.
Why use it?
It brings implementation differences, specification compliance, tests, quality, documentation, and security into one recorded evaluation.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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 commands/jayvee/aigon/feature-eval
Clone the repo
git clone --depth 1 https://github.com/jayvee/aigon

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for feature-eval

README.md
[![agentmods](https://agentmods.dev/badge/commands/jayvee/aigon/feature-eval.svg)](https://agentmods.dev/commands/jayvee/aigon/feature-eval)
Your own site
<a href="https://agentmods.dev/commands/jayvee/aigon/feature-eval"><img src="https://agentmods.dev/badge/commands/jayvee/aigon/feature-eval.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 932 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 98% copy Near-identical to another mod 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 5.1 $0.00010 $0.00932
Opus 5 $0.00005 $0.00466
Sonnet 5 $0.00002 $0.00186
Haiku 4.5 $0.00001 $0.00093

Measured 3d ago against content hash 01b9b943a3f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

feature-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 3d 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.

Origin

This is a copy

98% identical to afe — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/aigon/feature-eval.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aigon-feature-eval

Evaluate a feature implementation. Works in Drive mode (code review) and Fleet mode (comparison).

Argument Resolution

If no ID is provided or doesn't match an active feature, run aigon feature-list --active, filter to matches, and ask the user which.

Step 1: Run the CLI

aigon feature-eval {{args}}
# optional: --allow-same-model-judge    # suppress same-family bias warning

This records the evaluation lifecycle state, refreshes the generated view, creates ./docs/specs/features/evaluations/feature-{{args}}-eval.md, detects mode (Drive or Fleet), warns on same-family evaluator/implementer, and commits owned artifacts. The spec body is printed inline — use that copy; do not re-run aigon feature-spec.

Step 2: Review the implementation(s)

Drive Mode (code review)

  1. Read the implementation log: ./docs/specs/features/logs/feature-{{args}}-*-log.md
  2. git diff main...feature-{{args}}-*
  3. Check spec compliance, code quality, testing, documentation, security.

Fleet Mode (comparison)

For each agent worktree at ../feature-{{args}}-<agent>-*:

  • Read the implementation log from the worktree
  • Run git diff main...HEAD in each worktree
  • Check spec compliance

Bias guard: feature-eval warns automatically on same-family eval. Pass --allow-same-model-judge to suppress if intentional.

Step 3: Write the evaluation

Update ./docs/specs/features/evaluations/feature-{{args}}-eval.md.

Drive Mode

Complete the checklist (Spec Compliance, Code Quality, Testing, Documentation, Security) and add Strengths, Areas for Improvement, and an Approval decision (Approved / Needs Changes).

Fleet Mode

Use this exact structure — scoring table, then summary table, then Strengths/Weaknesses, then Recommendation.

| Criteria | cx | ag |
|---|---|---|
| Code Quality | /10 | /10 |
| Spec Compliance | /10 | /10 |
| Performance | /10 | /10 |
| Maintainability | /10 | /10 |
| **Total** | **/40** | **/40** |

Read the full file on GitHub · 88 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. 3d ago First seen · 88 lines · 10 tokens per session scan A 01b9b943a3f4

Subscribe to this mod's changes

feature-eval is a command published in the GitHub repository jayvee/aigon (25 stars, last pushed 5d ago), licensed Apache-2.0. It adds 10 tokens to every session and 932 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to afe, differing in 2 lines, and is treated as a copy.