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.
npx agentmods add skills/jayvee/aigon/aigon-research-evalnpx skills add jayvee/aigon --skill aigon-research-evalgit clone --depth 1 https://github.com/jayvee/aigonWrote 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.
[](https://agentmods.dev/skills/jayvee/aigon/aigon-research-eval)<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>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.
| Model | Per session | Once 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 |
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.
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:
- List all files in
./docs/specs/research-topics/03-in-progress/and./docs/specs/research-topics/04-in-evaluation/matchingresearch-*.md - If a partial ID or name was given, filter to matches
- Present the matching topics and ask the user to choose one
Recommended: Use a Different Model
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:
- Exact match: Same feature name from multiple agents = one entry, note all agents
- Similar concept: Different names but same idea = merge into one, pick the best name
- Related but distinct: Keep separate but note the relationship
- Unique: One agent only = keep, but flag for user attention
Present a consolidated table:
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.
- 5d ago First seen · 264 lines · 19 tokens per session scan A 7e9dff85bff3
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.
Other skills, from other repositories
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
local-frontend-check
Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.
ppt-review
Read this skill only after current officereview structural output and relevant rendered images exist. Do not use source code, a tool success flag, or the first-slide preview as a substitute for deck evidence.
package-installer
Install third-party open-source projects (a GitHub URL or a local git directory the user provides) as external packages. The project is cloned verbatim into the per-user packages directory — never edit, normalize, or reorganize its files.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.