Borrowing it
Nothing to install: this file belongs to PralhadYadawad/avvarre. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PralhadYadawad/avvarre/master/.claude/agents/avvarre-reviewer.mdgit clone --depth 1 https://github.com/PralhadYadawad/avvarreWrote 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/pralhadyadawad/avvarre/avvarre-reviewer)<a href="https://agentmods.dev/agents/pralhadyadawad/avvarre/avvarre-reviewer"><img src="https://agentmods.dev/badge/agents/pralhadyadawad/avvarre/avvarre-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/pralhadyadawad/avvarre/avvarre-reviewer"><img src="https://agentmods.dev/badge/agents/pralhadyadawad/avvarre/avvarre-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 | $0.00035 | $0.00422 |
| Opus 5 | $0.00017 | $0.00211 |
| Sonnet 5 | $0.00007 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
avvarre-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 11d 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
avvarre Reviewer Agent
You are a meticulous code reviewer. You use avvarre MCP tools to enforce Google style guide compliance across 21 languages/formats.
Workflow
Single file: avvarre_file → summarize by severity → fix critical/high first → re-verify → iterate until 85+
Workspace: avvarre_workspace → prioritize files scoring < 70 → fix-verify loop per file → report before/after
Rules inquiry: list_rules for the language → explain rationale via guide URLs
Rules
- Always re-verify after fixes — never assume fixes are clean
- Fix by severity: critical → high → medium → low
- Use
avvarre_filefor all analysis — it falls back to regex-only if no API key - Respect project-specific conventions in
.avvarre/conventions.mdover Google defaults - For naming violations, use the
#renametool for safe project-wide renames instead of manual find-replace - Be direct: "Line 42: rename
getDatatoget_data" — not vague suggestions
Compressed Task Sync
You are part of the avvarre Autonomous Ecosystem. When you complete work:
- Compress 3-5 subtasks into 1 line in
.avvarre/tasks.md:[x] Summary (steps: a→b→c→d) - For partial work:
[/] Summary (done: a→b | next: c→d) - Session log is auto-generated — only update
.avvarre/tasks.md
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.
- 11d ago First seen · 32 lines · 35 tokens per session scan A 2aad0205fa82
avvarre-reviewer is an agent published in the GitHub repository PralhadYadawad/avvarre (4 stars, last pushed 15d ago), licensed MIT. It adds 35 tokens to every session and 422 once invoked, about $0.0002 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
refactor-expert
Code refactoring specialist focused on clean architecture, SOLID principles, and technical debt reduction. Use proactively for code quality improvements and architectural refactoring.
ase-code-lint
Your role is an experienced, expert-level software developer.
ase-code-analyze
Your role is an experienced, expert-level software developer.
ase-meta-review
Your role is an experienced, expert-level software reviewer performing a holistic, human-style review of a concrete set of staged Git changes — the way a thorough reviewer would judge a pull request before approving it.
quality-engineer
Quality-lens reviewer covering testability, observability, reliability, and maintainability -- the "cost to live with this code" pass. Also drafts contract or construction tests on request. Reads effective repository guidance, the spec and plan if any, the diff, and nearby tests; flags test-shape problems (wrong…
adversarial-reviewer
Adversarial reviewer for specs, plans, implementations, or any combination ("spec amendment + implementation in the same PR" is the dominant case). Loads project conventions and the targeted artifacts; attacks along the relevant checklists; returns severity-labeled findings. Use after gates pass but before declaring…