What is formax-expanded-transcript-workflow?

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

Use it when changing Ctrl+O expanded transcripts, compact views, thinking persistence, or related clear and remount behavior.

It reduces guesswork about which code and documentation control keyboard shortcuts, rendering, persistence, and resets.

How yusifeng/formax configures Codex

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-expanded-transcript-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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yusifeng/formax/formax-expanded-transcript-workflow/github.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/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.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" 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. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00030	$0.00714
Opus 5.5	$0.00012	$0.00286
Sonnet 5.5	$0.00006	$0.00143
Haiku 4.5	$0.00003	$0.00071

Measured 2mo ago against content hash 3cac31d565b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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-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

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

2mo 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 (184 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 714 once invoked, about $0.0001 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.

Debugging ai assistant cli developer-tools ink

formax-expanded-transcript-workflow next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
formax-expanded-transcript-workflowyusifeng/formax	Skill	184	3mo ago	MIT	A	30	Codex
code_explorergoogle-gemini/gemini-cli	Skill	109k	yesterday	Apache-2.0	A	28	Gemini CLI
node-connectopenclaw/openclaw	Skill	394k	yesterday	MIT	A	39	Claude Code, Codex
node-inspect-debuggeropenclaw/openclaw	Skill	394k	yesterday	MIT	A	28	Claude Code, Codex
test-failure-explorerQwenLM/qwen-code	Skill	29k	yesterday	Apache-2.0	A	32	Claude Code, Codex
session-investigatorevalstate/fast-agent	Skill	4.0k	yesterday	Apache-2.0	A	68	Claude Code, Codex
smiles-validationsynthetic-sciences/openscience	Skill	4.3k	2d ago	Apache-2.0	A	24	Claude Code, Codex

formax: Skill for Codex