formax: Skill for Codex

.codex/skills/formax-repomix-handoff-workflow/SKILL.md

formax-repomix-handoff-workflow is a skill for Codex from yusifeng/formax. It costs 49 tokens per session (1,079 once invoked), scanned A, original, MIT.

A workflow for preparing a code handoff to another AI agent. It selects relevant repository files, packages them into a Repomix bundle, and writes a prompt with constraints and checks.

In plain words
What is it for?
Use it when another agent needs to investigate or change a Formax repository, with minimal, core, or full context bundles.
Why use it?
It reduces the chance of sending too much, too little, or stale project context. It also keeps handoff files named and organized consistently.

Skill for Codex

Written for Codex: installed under .codex/. Also seen: mentions Codex.

This is yusifeng/formax's own configuration. It tells Codex how to work on formax itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything formax configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yusifeng/formax. 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/yusifeng/formax/main/.codex/skills/formax-repomix-handoff-workflow/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/yusifeng/formax

Made for: Codex.

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 formax-repomix-handoff-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/yusifeng/formax/formax-repomix-handoff-workflow/github.svg)](https://agentmods.dev/skills/yusifeng/formax/formax-repomix-handoff-workflow)
Your own site
<a href="https://agentmods.dev/skills/yusifeng/formax/formax-repomix-handoff-workflow"><img src="https://agentmods.dev/badge/skills/yusifeng/formax/formax-repomix-handoff-workflow/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.

agentmods 80×15 button for formax-repomix-handoff-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/yusifeng/formax/formax-repomix-handoff-workflow"><img src="https://agentmods.dev/badge/skills/yusifeng/formax/formax-repomix-handoff-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,079 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00049 $0.01079
Opus 5 $0.00024 $0.00540
Sonnet 5 $0.00010 $0.00216
Haiku 4.5 $0.00005 $0.00108

Measured 11d ago against content hash 96f19b328a9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

formax-repomix-handoff-workflow 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/build-repomix.sh, scripts/check-handoff-artifacts.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.codex/skills/formax-repomix-handoff-workflow/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

formax-repomix-handoff-workflow

Goal

Create a clean handoff package for another AI with:

  • the smallest correct repomix bundle
  • a prompt that matches the target environment
  • explicit acceptance criteria and non-goals
  • predictable artifact naming + validation (so uploads stay consistent)

Where to change what

  • All handoff artifacts live in one folder: repomix-output/
  • Bundle output: repomix-output/repomix-<topic>-<tier>.txt
  • Handoff prompt: repomix-output/<topic>-handoff-prompt.md
  • File manifest notes: repomix-output/repomix-<topic>-files.md
  • Template references: references/prompt-templates.md

Required hygiene: each new pack run must clear previous files in repomix-output/ first, so users can upload that folder as-is without manual file picking.

Pack tiers (default taxonomy)

Use exactly one tier label in bundle filename:

  • minimal: changed runtime files + direct dependencies + adjacent tests.
  • core: minimal + only critical contract/design docs needed for intent.
  • full: broad context pack for deep investigations (cross-subsystem docs/tests).

Example names:

  • repomix-topic-minimal.txt
  • repomix-topic-core.txt
  • repomix-topic-full.txt

Patterns

  1. Classify target runtime first
  • Static consumer (e.g., WebGPT): cannot run local commands or tests.
  • Executable agent (repo access): can run local commands/tests.
  1. Pick a pack tier first (minimal / core / full)
  • Default to minimal.
  • Upgrade to core only when architecture/contracts matter.
  • Use full only when root cause plausibly spans multiple subsystems.
  1. Build the include set for that tier
  • Include changed runtime files + direct dependencies + adjacent tests.
  • Include only docs needed for intent/constraints at the chosen tier.
  • Avoid unrelated folders to keep context small.
  1. Pack with deterministic command (single folder, auto-clean)
bunx repomix . \
  --style plain \
  --no-git-sort-by-changes \
  -o repomix-output/repomix-<topic>-<tier>.txt \
  --include "<comma-separated-file-list>"

Or use the helper script:

bash .codex/skills/formax-repomix-handoff-workflow/scripts/build-repomix.sh \
  repomix-<topic>-<tier>.txt \
  "<comma-separated-file-list>"

The helper script will:

  • create repomix-output/ if missing
  • delete previous files under repomix-output/ (except .gitkeep)
  • write the new bundle into repomix-output/

Read the full file on GitHub · 113 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 113 lines · 49 tokens per session scan A 96f19b328a9e

Subscribe to this mod's changes

formax-repomix-handoff-workflow is a skill published in the GitHub repository yusifeng/formax (193 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 1,079 once invoked, about $0.0002 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 2026-08-30.