formax: Skill for Codex

.codex/skills/formax-slash-command-workflow/SKILL.md

formax-slash-command-workflow is a skill for Codex from yusifeng/formax. It costs 51 tokens per session (927 once invoked), scanned A, original, MIT.

A workflow for adding or changing slash commands, which are commands such as /permissions or /hooks entered inside a coding agent. It covers how commands are found, run, displayed, and passed into the next model turn.

In plain words
What is it for?
Use it to implement or update Formax slash commands, command discovery and dispatch, overlay dismissal messages, and command output handling.
Why use it?
It reduces mistakes where a command works internally but shows the wrong message, dismisses an overlay incorrectly, or sends the wrong information to the model.

Skill for Codex

Written for Codex: installed under .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-slash-command-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-slash-command-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/yusifeng/formax/formax-slash-command-workflow.svg)](https://agentmods.dev/skills/yusifeng/formax/formax-slash-command-workflow)
Your own site
<a href="https://agentmods.dev/skills/yusifeng/formax/formax-slash-command-workflow"><img src="https://agentmods.dev/badge/skills/yusifeng/formax/formax-slash-command-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 927 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.00927
Opus 5 $0.00026 $0.00464
Sonnet 5 $0.00010 $0.00185
Haiku 4.5 $0.00005 $0.00093

Measured 7d ago against content hash e86dddd43858, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

formax-slash-command-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 7d 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.

.codex/skills/formax-slash-command-workflow/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Formax slash command workflow

Goal

Use this skill when changing slash command discovery, dispatch, overlay dismissal output, or next-turn injection behavior.

Read First

  • docs/contracts/slash-command-contract.md
  • docs/contracts/semantics-contract.md when command behavior crosses canonical UI messages or routing
  • docs/contracts/config-settings-contract.md when the change touches /config

These docs are canonical. If stable behavior changes, update them before or with code.

Code Map

1) Command discovery + dispatch

  • packages/core/src/features/commands/registry.ts: command list/suggest/dispatch wiring
  • packages/core/src/features/commands/CommandStore.ts: disk scanning + precedence (project overrides user)
  • packages/core/src/features/semantics/core/commandRouting.ts: exact /clear / /compact and command-dispatch routing boundary

2) Command result contract (UI vs model)

  • packages/core/src/features/commands/contracts.ts: UiEffect / UiMessage / ModelEffect shapes
  • packages/core/src/features/commands/adapter.ts: maps command execution output → CommandResult
  • packages/core/src/features/repl/controller/send/send.ts: consumed slash handling, local_async, and injected-block plumbing

3) Overlay dismissal “subline output”

  • packages/core/src/features/repl/controller/ui/overlays.ts: overlay open/close + append “dismissed” sublines

4) REPL message plumbing + rendering

  • packages/core/src/features/repl/controller/send/send.ts: applies UiEffect.appendMessages to Msg
  • packages/core/src/screens/REPL.tsx: render msg.ui.kind === 'command_subline' as ⎿ ... (no )
  • packages/core/src/screens/REPL.slashSuggestions.test.tsx: duplicate command selection / preferredSlashSpecId

High-Signal Patterns

  • Pattern A: one-line overlay dismissal
    • append a single assistant Msg with ui.kind='command_subline'
    • keep copy stable unless the user explicitly requests copy changes
  • Pattern B: multi-line local output
    • split output into multiple command_subline rows
    • this is UI only; model injection remains separately controlled
  • Pattern C: inject-but-don't-spam
    • when a command needs to inform the model, keep UI output minimal and preserve recordForNextTurn / injected-block behavior separately

Read the full file on GitHub · 73 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. 7d ago First seen · 73 lines · 51 tokens per session scan A e86dddd43858

Subscribe to this mod's changes

formax-slash-command-workflow is a skill published in the GitHub repository yusifeng/formax (192 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 927 once invoked, about $0.0003 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.