A command for reviewing one feedback item and suggesting its type, severity, tags, possible duplicates, and next action. It requires a person to confirm the recommendation before changes are written.

Use it to triage feedback, find similar items, and decide whether to keep it, close it as a duplicate, turn it into a feature or research task, or mark it as not planned.

It reduces the manual effort of sorting feedback while keeping the final decision under human control.

afbt — Command for Claude Code by jayvee

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.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/jayvee/aigon/afbt.svg)](https://agentmods.dev/commands/jayvee/aigon/afbt)

Your own site

<a href="https://agentmods.dev/commands/jayvee/aigon/afbt"><img src="https://agentmods.dev/badge/commands/jayvee/aigon/afbt.svg" alt="Measured on agentmods" height="20"></a>

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 422 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	$0.00018	$0.00422
Opus 5	$0.00009	$0.00211
Sonnet 5	$0.00004	$0.00084
Haiku 4.5	$0.00002	$0.00042

Measured 3d ago against content hash b6998e6ae7b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

afbt 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

1 near-identical copy found in the catalogue:

feedback-triage — 91% identical, 2 lines differ

.claude/commands/afbt.md · 60 lines

What it actually says

aigon-feedback-triage

Run a triage loop for one feedback item with explicit human confirmation before writes.

Step 1: Load context

Run:

aigon feedback-triage {{args}}

Then gather broader context:

aigon feedback-list --all

Step 2: Produce triage recommendation

Use the feedback file content plus CLI output to propose:

type
severity
tags
duplicate candidates (based on title + summary similarity)
next action: keep, mark duplicate, promote to feature, promote to research, wont-fix

When duplicates are plausible, include candidate IDs with rationale.

Step 3: Ask for confirmation (required)

Before writing anything, present the proposed values and ask the user to confirm.

Do not apply triage changes until the user explicitly says yes.

Step 4: Apply only after confirmation

After confirmation, run:

aigon feedback-triage {{args}} --type <type> --severity <severity> --tags <tag1,tag2> --status <status> [--duplicate-of <ID>] --apply --yes

Notes:

Use --severity none to clear severity
Use --tags none to clear tags
Use --duplicate-of none to clear duplicate linkage
Duplicate status requires duplicate_of

Step 5: Verify outcome

Confirm the command output shows:

front matter updates applied
file moved to the correct feedback lifecycle folder for the new status

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.

3d ago First seen · 60 lines · 18 tokens per session scan A b6998e6ae7b0

Subscribe to this mod's changes

afbt is a command published in the GitHub repository jayvee/aigon (25 stars, last pushed 6d ago), licensed Apache-2.0. It adds 18 tokens to every session and 422 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.

Claude Code Project management agent-orchestration ai-agents cli codex developer-tools

afbt

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

Copies of this mod

What it actually says

aigon-feedback-triage

Step 1: Load context

Step 2: Produce triage recommendation

Step 3: Ask for confirmation (required)

Step 4: Apply only after confirmation

Step 5: Verify outcome

What this file has done since we first saw it

Other commands, from other repositories

report-issue

archive-tasks.en

block-task.en

check-task.en

create-task.en

import-issue.en