What is avvarre:autopilot?

A slash command that repeatedly checks the currently open file and fixes its style violations until its score reaches 90 or higher. It rechecks the file after every change and stops when progress stalls or 15 cycles are reached.

Use it to clean up naming and other reported style issues in one file, then see the before-and-after scores and the number of fixes made.

It removes the manual cycle of finding a style problem, fixing it and checking the result again. It also prevents unchecked fixes and avoids changing program logic.

How PralhadYadawad/avvarre configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/PralhadYadawad/avvarre/master/.claude/commands/avvarre-autopilot.md

Clone the repo

git clone --depth 1 https://github.com/PralhadYadawad/avvarre

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/pralhadyadawad/avvarre/avvarre-autopilot/github.svg)](https://agentmods.dev/commands/pralhadyadawad/avvarre/avvarre-autopilot)

Your own site

<a href="https://agentmods.dev/commands/pralhadyadawad/avvarre/avvarre-autopilot"><img src="https://agentmods.dev/badge/commands/pralhadyadawad/avvarre/avvarre-autopilot/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/pralhadyadawad/avvarre/avvarre-autopilot"><img src="https://agentmods.dev/badge/commands/pralhadyadawad/avvarre/avvarre-autopilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 298 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00028	$0.00298
Opus 5	$0.00014	$0.00149
Sonnet 5	$0.00006	$0.00060
Haiku 4.5	$0.00003	$0.00030

Measured 11d ago against content hash 1aa03e99330a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

avvarre:autopilot 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.

.claude/commands/avvarre-autopilot.md · 29 lines

What it actually says

/avvarre:autopilot

Autonomously fix a file until it reaches Grade A (score 90+).

Instructions

Determine the currently open file
Run avvarre_file on the file — record the initial score
Loop: a. If score >= 90 → go to step 4 b. Pick the highest-severity violation c. Fix it using the suggested fix. For naming violations, use the #rename tool for safe project-wide renames instead of manual find-replace. d. Run avvarre_file again → record new score e. If score decreased or is unchanged after 3 consecutive iterations → stop loop, report blocker f. Repeat from 3a
Done: Report before/after scores and total violations fixed.

Guardrails

Max 15 iterations — if not Grade A after 15 fix-verify cycles, stop and report remaining violations
Never skip re-verification — fixes can introduce new violations
Preserve semantics — only fix style violations, never change logic
Log progress — after completion, update .avvarre/tasks.md with results

Changes

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 · 29 lines · 28 tokens per session scan A 1aa03e99330a

Subscribe to this mod's changes

avvarre:autopilot is a command published in the GitHub repository PralhadYadawad/avvarre (4 stars, last pushed 14d ago), licensed MIT. It adds 28 tokens to every session and 298 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 2026-08-31.

Claude Code Code review agent-tools agentic-ai agentic-coding ai-memory code-quality

avvarre: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/avvarre:autopilot

Instructions

Guardrails

What this file has done since we first saw it

Other commands, from other repositories

github

review

conventions-check

review

review-prs

brief-refresh