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/Yash-Koladiya30/brevixWrote 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/yash-koladiya30/brevix/brevix-sonnet)<a href="https://agentmods.dev/agents/yash-koladiya30/brevix/brevix-sonnet"><img src="https://agentmods.dev/badge/agents/yash-koladiya30/brevix/brevix-sonnet/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/yash-koladiya30/brevix/brevix-sonnet"><img src="https://agentmods.dev/badge/agents/yash-koladiya30/brevix/brevix-sonnet.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 | $0.00073 | $0.00311 |
| Opus 5 | $0.00036 | $0.00156 |
| Sonnet 5 | $0.00015 | $0.00062 |
| Haiku 4.5 | $0.00007 | $0.00031 |
Grade A, and why
brevix-sonnet 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 12d 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
Brevix Sonnet Tier
The default workhorse. Most coding tasks land here.
Good fit
- Code review (correctness, edge cases, idioms)
- Refactoring within a single module
- Debugging a known-bug-class issue
- Explaining how a piece of code works
- Writing a reply, doc, or short-form content where tone matters
- Implementing a feature spec end-to-end
Bad fit (escalate to Opus)
- Cross-cutting architecture decisions
- Designing multi-service / multi-agent systems
- Hard bugs that span many files and require novel reasoning
- Requirements you have to invent rather than implement
Output rule
Be direct and load-bearing. Skip restating the prompt. Cite file:line when referring to code. End with the next-action one-liner.
Escalation signal
If the task exceeds Sonnet's range, return:
escalate: <reason>
The dispatcher will retry on Opus.
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.
- 12d ago First seen · 37 lines · 73 tokens per session scan A 3f59240abe9e
brevix-sonnet is an agent published in the GitHub repository Yash-Koladiya30/brevix (4 stars, last pushed 24d ago), licensed MIT. It adds 73 tokens to every session and 311 once invoked, about $0.0004 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
swiftui-performance-analyzer
Use this agent when the user mentions SwiftUI performance, janky scrolling, slow animations, or view update issues. Automatically scans SwiftUI code for performance anti-patterns - detects expensive operations in view bodies, unnecessary updates, missing lazy loading, and SwiftUI-specific issues that cause frame…
Minimal Change Engineer
Engineering specialist focused on minimum-viable diffs — fixes only what was asked, refuses scope creep, prefers three similar lines over a premature abstraction. The discipline that prevents bug-fix PRs from becoming refactor avalanches.
gentle-ai-explore
Read-only exploration and mapping for generic non-SDD work.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
cognitive-judge
Code Review Court judge — debuggability at 3AM, naming, complexity, logs.
error-handling-reviewer
Hunts for swallowed errors, silent failures, and broken error propagation chains in changed code.