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.
git 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/commands/jayvee/aigon/research-review)<a href="https://agentmods.dev/commands/jayvee/aigon/research-review"><img src="https://agentmods.dev/badge/commands/jayvee/aigon/research-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/jayvee/aigon/research-review"><img src="https://agentmods.dev/badge/commands/jayvee/aigon/research-review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00754 |
| Opus 5.5 | $0.00000 | $0.00302 |
| Sonnet 5.5 | $0.00000 | $0.00151 |
| Haiku 4.5 | $0.00000 | $0.00075 |
Grade A, and why
research-review 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 1mo 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aigon-research-review
Review research findings for rigor, completeness, and accuracy, making targeted improvements where needed.
Use case: After research agents submit their findings, a different agent reviews the quality of the research and refines the findings. This provides cross-agent quality assurance before evaluation.
Argument Resolution
If no ID is provided, or the ID doesn't match existing research:
- Run
aigon research-list --active - If a partial ID or name was given, filter to matches
- Present the matching research and ask the user to choose one
Step 1: Run the CLI command
aigon research-review {{args}}
Step 2: Read the research spec
Read the research topic spec to understand what was being investigated:
Look in docs/specs/research-topics/03-in-progress/ for the research spec matching the ID.
Step 3: Read the findings
Read all agent findings files to understand what was researched:
ls docs/specs/research/logs/research-{{ARG1_SYNTAX}}-*-findings.md
Read each findings file.
Step 4: Review the findings
Signal review start immediately:
aigon agent-status reviewing
Enter Research Review Mode with this checklist:
Methodology rigor
- Are the research methods sound and appropriate for the questions asked?
- Are conclusions supported by the evidence presented?
- Are there logical gaps or unsupported claims?
Completeness
- Are all research questions from the spec addressed?
- Are there obvious gaps or areas that were skipped?
- Are edge cases and alternative perspectives considered?
Accuracy
- Are factual claims verifiable?
- Are sources cited where appropriate?
- Are there contradictions within the findings?
Evidence quality
- Is the evidence sufficient to support the conclusions?
- Are examples concrete and relevant?
- Are trade-offs honestly presented?
Step 5: Make refinements
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.
- 1mo ago First seen · 115 lines · 0 tokens per session scan A ecff498beb1e
research-review is a command published in the GitHub repository jayvee/aigon (26 stars, last pushed 12d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 754 tokens. 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 2026-09-03.
Other commands, from other repositories
brain-stats
Show claudectl brain learning metrics — accuracy, correction rate, and effectiveness.
stop
Gracefully close the Vibe Squad tmux session from inside Chrono.
mach12:issue-review
Read a GitHub issue and all comments, review the implementation plan, and present findings.
mach12:gh-pr-read
Read a GitHub pull request's title, body, and all top-level PR conversation comments; optionally locate an HTML-marker comment.
scramjet:troubleshoot
Diagnose unexpected command behavior and recommend safe resolution.
checklist
Generate a custom checklist for the current feature based on user requirements.