agentmods.dev

formax-expanded-transcript-workflow

formax-expanded-transcript-workflow is a skill for Claude Code, Codex from yusifeng/formax. It costs 30 tokens per session (714 once invoked), scanned A, original, MIT.

A workflow guide for changing and debugging an REPL’s expanded transcript view, including how its displayed conversation and internal reasoning are kept consistent.

In plain words
What is it for?
Use it when changing Ctrl+O expanded transcripts, compact views, thinking persistence, or related clear and remount behavior.
Why use it?
It reduces guesswork about which code and documentation control keyboard shortcuts, rendering, persistence, and resets.

Skill for Claude CodeCodex

not rated 192 +1 1mo ago A scan 30 tokens original MIT
View the source file yusifeng/formax
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 skills/yusifeng/formax/formax-expanded-transcript-workflow
Any agent
npx skills add yusifeng/formax --skill formax-expanded-transcript-workflow
Clone the repo
git clone --depth 1 https://github.com/yusifeng/formax

Made for: Claude Code, 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-expanded-transcript-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/yusifeng/formax/formax-expanded-transcript-workflow.svg)](https://agentmods.dev/skills/yusifeng/formax/formax-expanded-transcript-workflow)
Your own site
<a href="https://agentmods.dev/skills/yusifeng/formax/formax-expanded-transcript-workflow"><img src="https://agentmods.dev/badge/skills/yusifeng/formax/formax-expanded-transcript-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 714 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 $0.00030 $0.00714
Opus 5 $0.00015 $0.00357
Sonnet 5 $0.00006 $0.00143
Haiku 4.5 $0.00003 $0.00071

Measured 4d ago against content hash 3cac31d565b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

formax-expanded-transcript-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 4d 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-expanded-transcript-workflow/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

formax-expanded-transcript-workflow

Goal

Use this skill when changing Ctrl+O expanded transcript behavior, thinking persistence, or compact / expanded projection boundaries in the REPL.

Read First

  • docs/contracts/transcript-surface-contract.md
  • docs/contracts/semantics-contract.md
  • docs/runbooks/repl-surface-debugging.md when the change can affect clear / remount behavior

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

If the change touches clear / remount ownership directly, also use formax-surface-reset-workflow.

Code Map

  • Key handling: packages/core/src/screens/repl/hotkeys.ts
  • View wiring + footer: packages/core/src/screens/REPL.tsx
  • Compact projection: packages/core/src/screens/repl/compactProjection.ts
  • Transcript rendering: packages/core/src/screens/repl/transcript.tsx
  • Thinking persistence: packages/core/src/features/repl/controller/streaming/streaming.ts
  • Expanded Transcript panels: packages/core/src/screens/repl/panels.tsx
  • Compact command lifecycle: packages/core/src/features/repl/controller/send/send.ts
  • Surface reset owner: packages/core/src/screens/repl/useSurfaceTransitionManager.ts

High-Signal Patterns

  • No fake thinking:
    • thinking_delta is the only source of truth
    • never synthesize thinking rows from timers or summaries
  • Avoid Static hacks for toggles:
    • Static is append-only; if content must disappear, use reset / remount ownership instead of trying to "unrender" it
  • One footer:
    • prefer a single global footer; avoid per-panel footer duplication
  • Compact ordering contract:
    • keep banner -> summary (expanded only) -> > /compact ... -> compact subline
  • UI vs LLM orthogonality:
    • transcript slicing and ui.kind remain independent from prompt-history packing and reminder injection

Minimal Workflow

  1. Lock the semantic source first: thinking_delta persistence and transcript projection rules before renderer polish.
  2. Keep default transcript low-noise and Expanded Transcript read-only.
  3. Preserve compact / expanded ordering before adjusting footer or panel layout.
  4. If clear / remount logic changes, route through the shared surface reset path instead of local Static workarounds.
  5. Run the regression set below before review.

Read the full file on GitHub · 68 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. 4d ago First seen · 68 lines · 30 tokens per session scan A 3cac31d565b0

Subscribe to this mod's changes

formax-expanded-transcript-workflow is a skill published in the GitHub repository yusifeng/formax (192 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 714 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.

Debuggingaiassistantclideveloper-toolsink
Related

Other skills, from other repositories

google-drive-sheets

Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.

yc-software/qm · 31 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

linear

Search, read, create, and update the user's Linear issues, projects, and comments through per-user OAuth.

yc-software/qm · 24 tokens

slack-drafts

Create Slack message drafts in the user's own composer, as the user, through their per-user Slack OAuth. Drafting only — the user reviews and sends from Slack.

yc-software/qm · 38 tokens

deploy-qm

Deploy the QM package from an organization-owned repository into Fly.io or AWS, onboard an administrator, configure connectors, and optionally activate Slack.

yc-software/qm · 31 tokens

connect-apps

Connect an administrator-enabled SaaS app for a user with a one-time OAuth consent link.

yc-software/qm · 22 tokens