agentmods.dev

formax: Skill for Codex

.codex/skills/formax-semantics-parity-workflow/SKILL.md

formax-semantics-parity-workflow is a skill for Codex from yusifeng/formax. It costs 49 tokens per session (1,042 once invoked), scanned A, original, MIT.

A workflow for keeping behavior identical across Formax's terminal interface, app server, and web interface. It separates shared meaning and event order from the code that displays those results in each interface.

In plain words
What is it for?
Use it when changing shared session behavior, input lifecycles, tool sequencing, replay, mode changes, or ordering across TUI and Web.
Why use it?
It prevents the same action from behaving differently depending on where it is used, especially for modes, input, tools, replay, and event ordering.

Skill for Codex

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

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 →

not rated 184repo +8 3mo ago A scan SkillSpector: pass 49 tokens original MIT
View source ↗ yusifeng/formax
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-semantics-parity-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-semantics-parity-workflow

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/yusifeng/formax/formax-semantics-parity-workflow"><img src="https://agentmods.dev/badge/skills/yusifeng/formax/formax-semantics-parity-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 1,042 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 $0.01042
Opus 5.5 $0.00020 $0.00417
Sonnet 5.5 $0.00010 $0.00208
Haiku 4.5 $0.00005 $0.00104

Measured 2mo ago against content hash 4cc816f21b09, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

formax-semantics-parity-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 2mo 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-semantics-parity-workflow/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

formax-semantics-parity-workflow

Goal

Use this skill when changing behavior that must stay consistent across TUI, app-server, and Web: mode, input lifecycle, tool sequencing, replay, or ordering.

Read First

  • docs/contracts/semantics-contract.md
  • docs/contracts/app-server-interaction-contract.md
  • docs/frontend/app-server-ui-spec.md
  • docs/contracts/interactive-input-contract.md when input lifecycle changes

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

Code Map

1) Semantic single source of truth

  • packages/core/src/features/semantics/*
    • canonicalEvents.ts
    • transcriptProjection.ts
    • modeSemantics.ts
    • replModeTransition.ts
    • turnInputBuilder.ts
    • inputStateMachine.ts

2) App-server contract emit / restore

  • packages/core/src/app-server/turnRunner.ts
  • packages/core/src/app-server/server.ts
  • packages/core/src/app-server/threadStore.ts
  • packages/core/src/app-server/store/sessionEventReader.ts
  • packages/core/src/app-server/turn/inputStore.ts

3) TUI adapter (renderer can differ, semantics cannot)

  • packages/core/src/features/repl/controller/send/send.ts
  • packages/core/src/features/repl/controller/streaming/streaming.ts
  • packages/core/src/features/repl/useReplController.ts

4) Web adapter (renderer can differ, semantics cannot)

  • packages/web-reference-react/src/eventAdapters.ts
  • packages/web-reference-react/src/App.tsx
  • packages/web-reference-react/src/store.ts
  • packages/web-reference-react/src/turnEventCursor.ts

5) Canonical docs to keep in sync

  • docs/contracts/semantics-contract.md
  • docs/contracts/app-server-interaction-contract.md
  • docs/frontend/app-server-ui-spec.md
  • docs/contracts/interactive-input-contract.md when input lifecycle changes

High-Signal Patterns

  • Semantic-first implementation order:
    1. define contract / event shape / state transition
    2. update shared semantics
    3. update app-server emit / replay state
    4. update TUI and Web adapters
    5. update renderer-only UI last
  • Ordering discipline:
    • replaySeq is the primary ordering key
    • traceId/seq are diagnostics and turn-local hints, not global order
    • on replay gap, rebuild from semantic baseline; do not keep stitching stale tails
  • Tool semantics discipline:
    • keep toolUseId -> toolName sticky behavior in semantics / adapter path
    • never depend on UI copy to infer tool state
  • Mode/input discipline:
    • mode is a semantic transition, not just a visual toggle
    • input lifecycle remains a finite-state machine, not ad-hoc UI flags

Read the full file on GitHub · 102 lines

Files

What ships with it

1 file 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. 2mo ago First seen · 102 lines · 49 tokens per session scan A 4cc816f21b09

Subscribe to this mod's changes

formax-semantics-parity-workflow is a skill published in the GitHub repository yusifeng/formax (184 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 1,042 once invoked, about $0.0002 per session on Opus 5.5. 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.

Frontendaiassistantclideveloper-toolsink
Related

formax-semantics-parity-workflow compared with skills from other repositories

formax-semantics-parity-workflow next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
formax-semantics-parity-workflowyusifeng/formaxSkill1843mo agoMITA49Codex
unbrokerKevRojo/DulusSkill5083d agoGPL-3.0A15Claude Code, Codex
obsidian-basesKevRojo/DulusSkill5083d agoGPL-3.0A63Claude Code, Codex
json-canvasKevRojo/DulusSkill5083d agoGPL-3.0A54Claude Code, Codex
obsidian-markdownKevRojo/DulusSkill5083d agoGPL-3.0A105Claude Code, Codex
obsidian-cliKevRojo/DulusSkill5083d agoGPL-3.0A102Claude Code, Codex
defuddleKevRojo/DulusSkill5083d agoGPL-3.0A74Claude Code, Codex