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.
git clone --depth 1 https://github.com/jayvee/aigonWrote 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/commands/jayvee/aigon/feature-code-revise)<a href="https://agentmods.dev/commands/jayvee/aigon/feature-code-revise"><img src="https://agentmods.dev/badge/commands/jayvee/aigon/feature-code-revise.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.01227 |
| Opus 5 | $0.00009 | $0.00613 |
| Sonnet 5 | $0.00003 | $0.00245 |
| Haiku 4.5 | $0.00002 | $0.00123 |
Grade A, and why
feature-code-revise scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
98% identical to afrv — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aigon-feature-code-revise
A reviewing agent has just committed fixes (or notes) on this feature branch. Your job — as the implementing agent — is to read what the reviewer did, then decide how to respond: accept, revert, or modify.
Step 0: Resolve the feature ID
If the user already passed an explicit feature ID as the command argument, use that ID and skip to Step 1.
Otherwise — the primary path — infer the ID from the current branch. You should be running this inside the implementation worktree:
BRANCH=$(git branch --show-current)
echo "Branch: $BRANCH"
Expected branch shape: feature-<slug>-<agent> (e.g. feature-check-review-skill-command-cc).
Parse the <slug> out of the branch name (strip the feature- prefix and the trailing -<agent> suffix where agent is one of cc, cx, cu, op, km, am, ag, cp). Then resolve the slug to a feature ID by matching against aigon feature-list --active:
aigon feature-list --active
Find the row whose name matches the slug and read its ID.
If the branch is main or doesn't match the feature-<slug>-<agent> pattern: STOP. Print this one-liner and do nothing else:
Can't infer feature ID — run this inside the feature worktree, or pass an explicit ID (e.g.
/aigon:feature-code-revise 230).
Do not guess. Do not prompt the user to pick from a list — that's noise. Just stop.
Step 1: Signal start of revision
Before reading the review, signal that you are now actively addressing the code review. This makes the dashboard reflect what you're doing in real time, and emits a lifecycle event the AutoConductor uses to detect stalls.
aigon agent-status addressing-code-review
Step 2: Find the review commits
Look at every commit on this branch that came from a reviewer:
git log --oneline --grep='^fix(review)\|^docs(review)' main..HEAD
For broader context (your own implementation commits too), also run:
git log --oneline main..HEAD
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 · 122 lines · 17 tokens per session scan A 37b1139c068d
feature-code-revise is a command published in the GitHub repository jayvee/aigon (25 stars, last pushed 6d ago), licensed Apache-2.0. It adds 17 tokens to every session and 1,227 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to afrv, differing in 2 lines, and is treated as a copy.
Other commands, from other repositories
request-review-plan
Request Code Review Phases 1-2: Planning scope and assembling reviewer context.
undo-commit
Soft-undo the last commit. Restores its changes as staged, leaves working tree intact. Refuses if HEAD is already pushed to a tracked remote.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
hatch3r-pr-resolve
Read open PR comments, evaluate each against current code via the rigor contract, implement accepted findings, reply inline. Multi-platform.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
Stage, commit, and optionally ship further. Pass an escalation token (push, pr, merge, squash, squash merge) to skip the prompt. With no token, commits then asks how far to ship. Delegates message format to the atomic-git-discipline skill.