afd

afd is a command for Claude Code from jayvee/aigon. It costs 19 tokens per session (1,674 once invoked), scanned A, original, Apache-2.0.

A command that guides a coding agent through implementing a planned feature in a branch or worktree. It also supports iterate mode, which starts fresh agent sessions until validation passes or the limit is reached.

In plain words
What is it for?
Use it to implement features in Drive or Fleet mode, optionally with repeated validation attempts and limits on the number of iterations.
Why use it?
It removes the need to repeatedly explain the feature plan and manage the implementation workflow by hand.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents; mentions AGENTS.md.

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/afd
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 afd

README.md
[![agentmods](https://agentmods.dev/badge/commands/jayvee/aigon/afd.svg)](https://agentmods.dev/commands/jayvee/aigon/afd)
Your own site
<a href="https://agentmods.dev/commands/jayvee/aigon/afd"><img src="https://agentmods.dev/badge/commands/jayvee/aigon/afd.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,674 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 $0.00019 $0.01674
Opus 5 $0.00010 $0.00837
Sonnet 5 $0.00004 $0.00335
Haiku 4.5 $0.00002 $0.00167

Measured 2d ago against content hash 04237288da3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

afd 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 2d 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/afd.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aigon-feature-do

RUN THIS FIRST — no preamble, no --help, no file searches:

aigon feature-do {{args}}

This prints the feature spec inline. Read the output, then follow the steps below. Do NOT search for spec files, do NOT run aigon --help, do NOT hunt for the aigon source. Just run the command above.

Implement a feature. Works in Drive mode (branch), Drive worktree, and Fleet mode (competition).

Worktree invariant: you are already inside the correct repo. If aigon fails, read the error — do NOT try to introspect the tool's internals.

Argument Resolution

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

Step 1: Attach to the workspace

aigon feature-do {{args}}

Only run /aigon:feature-start {{args}} if the feature branch/worktree does not exist yet.

To run in Autopilot mode — iterate loop where a fresh agent session is spawned each iteration until validation passes:

aigon feature-do {{ARG1_SYNTAX}} --iterate

Optional flags: --max-iterations=N (default 5) · --agent=<id> · --dry-run

What is iterate mode? The iterate technique runs an agent in a loop: implement → validate → if fail, repeat with fresh context until success or max iterations. Add a ## Validation section to your feature spec to define feature-specific checks alongside project-level validation.

If the CLI fails with "Could not find feature in in-progress" and you're in a worktree: the spec move was likely not committed before the worktree was created. Fix by running these commands from the worktree:

SPEC_PATH=$(aigon feature-spec {{ARG1_SYNTAX}})
git checkout main -- "$SPEC_PATH"
git commit -m "chore: sync spec to worktree branch"

Step 2: Read the spec (already inlined)

The spec body was printed inline by feature-do above. Use that copy. Do not re-read from disk and do not re-run aigon feature-spec — the inline copy is authoritative.

Read the full file on GitHub · 125 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. 2d ago First seen · 125 lines · 19 tokens per session scan A 04237288da3d

Subscribe to this mod's changes

afd is a command published in the GitHub repository jayvee/aigon (25 stars, last pushed 5d ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,674 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.