aigon-research-eval

aigon-research-eval is a skill for Claude Code, Codex from jayvee/aigon. It costs 19 tokens per session (2,294 once invoked), scanned A, original, Apache-2.0.

A research evaluation step that combines findings from all research agents and updates the main research document with feature recommendations.

In plain words
What is it for?
Use it to read all findings, synthesize them, help choose features, and update the research topic.
Why use it?
It turns separate research notes into one reviewed summary and moves the topic into an evaluation stage.

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/jayvee/aigon/aigon-research-eval
Any agent
npx skills add jayvee/aigon --skill aigon-research-eval
Clone the repo
git clone --depth 1 https://github.com/jayvee/aigon

Made for: Claude Code, Codex.

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 aigon-research-eval

README.md
[![agentmods](https://agentmods.dev/badge/skills/jayvee/aigon/aigon-research-eval.svg)](https://agentmods.dev/skills/jayvee/aigon/aigon-research-eval)
Your own site
<a href="https://agentmods.dev/skills/jayvee/aigon/aigon-research-eval"><img src="https://agentmods.dev/badge/skills/jayvee/aigon/aigon-research-eval.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,294 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 $0.00019 $0.02294
Opus 5 $0.00010 $0.01147
Sonnet 5 $0.00004 $0.00459
Haiku 4.5 $0.00002 $0.00229

Measured 5d ago against content hash 7e9dff85bff3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aigon-research-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 5d 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/aigon-research-eval/SKILL.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aigon-research-eval

Evaluate and synthesize research findings from ALL agents, help the user select features, and update the main research document. This transitions research from in-progress to in-evaluation (matching the feature pipeline).

Argument Resolution

If no ID is provided, or the ID doesn't match an existing topic in progress or in-evaluation:

  1. List all files in ./docs/specs/research-topics/03-in-progress/ and ./docs/specs/research-topics/04-in-evaluation/ matching research-*.md
  2. If a partial ID or name was given, filter to matches
  3. Present the matching topics and ask the user to choose one

For unbiased evaluation, use a different model than those that conducted the research.

claude --model sonnet
/aigon-research-eval 05

Step 1: Run the CLI command

IMPORTANT: You MUST run this command first. It transitions the engine state to evaluating and refreshes the generated lifecycle view.

aigon research-eval $1

Step 2: Read All Findings

Find and read ALL findings files:

docs/specs/research-topics/logs/research-{ID}-*-findings.md

Also read the main research topic:

docs/specs/research-topics/04-in-evaluation/research-{ID}-*.md

(If not found in 04-in-evaluation/, check 03-in-progress/.)

Step 3: Synthesize Findings

Present to the user:

Consensus

What all agents agree on.

Divergent Views

Where agents disagree and why - be specific about which agent said what.

Step 4: Consolidate Features

Extract the ## Suggested Features table from each agent's findings file.

Deduplication rules:

  1. Exact match: Same feature name from multiple agents = one entry, note all agents
  2. Similar concept: Different names but same idea = merge into one, pick the best name
  3. Related but distinct: Keep separate but note the relationship
  4. Unique: One agent only = keep, but flag for user attention

Present a consolidated table:

Read the full file on GitHub · 264 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. 5d ago First seen · 264 lines · 19 tokens per session scan A 7e9dff85bff3

Subscribe to this mod's changes

aigon-research-eval is a skill published in the GitHub repository jayvee/aigon (24 stars, last pushed 4d ago), licensed Apache-2.0. It adds 19 tokens to every session and 2,294 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