afr

afr is a command for Claude Code from jayvee/aigon. It costs 21 tokens per session (2,369 once invoked), scanned A, original, Apache-2.0.

A command that reviews another agent's feature implementation and makes targeted fixes when needed. It is a write-capable review, meaning it can change the code and commit those fixes.

In plain words
What is it for?
Use it to review an active feature, patch safe problems, commit review fixes, and leave notes only for issues that need further decisions.
Why use it?
It catches implementation problems and can resolve concrete issues during the review instead of only reporting them.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

Install

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.

agentmods
npx agentmods add commands/jayvee/aigon/afr
Clone the repo
git clone --depth 1 https://github.com/jayvee/aigon

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.

agentmods badge for afr

README.md
[![agentmods](https://agentmods.dev/badge/commands/jayvee/aigon/afr.svg)](https://agentmods.dev/commands/jayvee/aigon/afr)
Your own site
<a href="https://agentmods.dev/commands/jayvee/aigon/afr"><img src="https://agentmods.dev/badge/commands/jayvee/aigon/afr.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,369 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.02369
Opus 5 $0.00010 $0.01184
Sonnet 5 $0.00004 $0.00474
Haiku 4.5 $0.00002 $0.00237

Measured 3d ago against content hash 344c665b528f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

afr 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 3d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/commands/afr.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aigon-feature-code-review

Perform a code review on another agent's implementation, making targeted fixes where needed. Use a different model than the implementer for best results.

You are doing a write-capable review pass, not a read-only review report. Ignore any default "code review means findings-only" behavior for this task; this command is specifically a review-with-fixes workflow.

Your default action is:

  1. identify a concrete issue
  2. patch it in the feature worktree
  3. commit it with fix(review): ...
  4. leave only residual issues in notes

Do not stop at describing a fix if you can safely make it yourself. A findings-only review is valid only when:

  • the implementation is genuinely clean
  • the remaining issue requires a broader architectural or product decision
  • the issue is ambiguous and the correct behavior is not clear from the spec
  • you are blocked by missing context or infrastructure you cannot safely change

Argument Resolution

If no ID is provided or doesn't match an active feature, run aigon feature-list --active, filter to matches, and ask the user.

Step 1: Gather all context (one tool call)

Run this entire block in a single shell execution — do not split it up. It fetches branch info, the full diff, and the implementation log in one shot so you can review immediately without extra round-trips.

You MUST commit review changes to the FEATURE WORKTREE, never to main.

BRANCH=$(git branch --show-current)
FEATURE_BRANCH=$(git branch --list 'feature-{{args}}-*' | head -1 | tr -d ' *')
WORKTREE=$(git worktree list | grep "feature-{{args}}" | awk '{print $1}')
echo "=== WORKSPACE ==="
echo "Current: $BRANCH  Feature: $FEATURE_BRANCH  Worktree: $WORKTREE"
echo "=== DIFF ==="
git diff "main...${FEATURE_BRANCH:-HEAD}"
echo "=== IMPLEMENTATION LOG ==="
cat docs/specs/features/logs/feature-{{args}}-*-log.md 2>/dev/null || echo "(no log found)"
aigon agent-status reviewing

The spec body was printed inline by the launching CLI — use that copy for acceptance criteria.

Read the full file on GitHub · 211 lines

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.

  1. 3d ago First seen · 211 lines · 21 tokens per session scan A 344c665b528f

Subscribe to this mod's changes

afr is a command published in the GitHub repository jayvee/aigon (25 stars, last pushed 5d ago), licensed Apache-2.0. It adds 21 tokens to every session and 2,369 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 2026-09-03.