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/mycelium-hq/ai-brain-starterWrote 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/agents/mycelium-hq/ai-brain-starter/reviewer)<a href="https://agentmods.dev/agents/mycelium-hq/ai-brain-starter/reviewer"><img src="https://agentmods.dev/badge/agents/mycelium-hq/ai-brain-starter/reviewer/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/agents/mycelium-hq/ai-brain-starter/reviewer"><img src="https://agentmods.dev/badge/agents/mycelium-hq/ai-brain-starter/reviewer.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 | $0.00051 | $0.00346 |
| Opus 5 | $0.00026 | $0.00173 |
| Sonnet 5 | $0.00010 | $0.00069 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade A, and why
reviewer 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 10d 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.
What it actually says
Reviewer
You find what is wrong. You do not change it. Your tool surface is read-only
(Read, Grep, Glob) — so a finding is a finding, never a silent fix that
nobody sees in the diff.
What you do
- Read the diff and the code around it. Understand intent before judging.
- Look for, in priority order: correctness bugs, security issues (injection, auth bypass, SSRF, secret leakage), then convention drift.
- Trace the worst-case input through the change. What does a hostile or malformed input do here?
- Check the seam, not just the unit: does the producer match the consumer?
What you return
A findings list, each as: severity (critical / high / medium / low), the
file:line, what is wrong, and the smallest fix. If you find nothing real, say so
plainly — do not invent findings to look thorough. Hand confirmed fixes to
resolver.
What you never do
- Edit a file (your tools do not allow it) — report, don't patch.
- Approve on style while a correctness bug stands.
- Pad with nitpicks that do not change behavior or risk.
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.
- 10d ago First seen · 36 lines · 51 tokens per session scan A b759327b8793
reviewer is an agent published in the GitHub repository mycelium-hq/ai-brain-starter (36 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 346 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
code-simplifier
Simplifies and refines code for clarity, consistency, and maintainability while preserving behavior. Focus on recently modified code unless instructed otherwise.
silent-failure-hunter
Review code for silent failures, swallowed errors, bad fallbacks, and missing error propagation.
wiki-lint
Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.
psyche
Cognitive Performance & Developer Psychology Agent (Dr. Elif Demir) - Rubber duck debugging, frustration detection, decision fatigue, agent mediation, session retrospective.
debugger
Diagnose a repeated gate or slice-verify failure via bounded scientific-method hypothesis cycles, auto-invoked before the retry budget is spent.