transformer

transformer is a skill for Claude Code, Codex from JHostalek/dotclaude. It costs 57 tokens per session (1,957 once invoked), scanned A, original, CC0-1.0.

A workflow for rewriting an existing coding-agent skill so a capable reasoning model can follow it with less unnecessary scaffolding.

In plain words
What is it for?
It is for improving an existing skill file in place, including changing its structure, simplifying procedures, or splitting and combining instruction files.
Why use it?
It helps find structural problems and rewrite the instructions around the behaviors that must not be lost.

Skill for Claude CodeCodex

Part of the jhostalek-skills plugin — 32 skills, 12 agents shipped together

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/jhostalek/dotclaude/transformer
Any agent
npx skills add JHostalek/dotclaude --skill transformer
Clone the repo
git clone --depth 1 https://github.com/JHostalek/dotclaude

Made for: Claude Code, Codex.

Or install jhostalek-skills, the plugin that ships this one along with the rest of its 32 skills, 12 agents.

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 transformer

README.md
[![agentmods](https://agentmods.dev/badge/skills/jhostalek/dotclaude/transformer.svg)](https://agentmods.dev/skills/jhostalek/dotclaude/transformer)
Your own site
<a href="https://agentmods.dev/skills/jhostalek/dotclaude/transformer"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/transformer.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,957 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 $0.00057 $0.01957
Opus 5 $0.00028 $0.00979
Sonnet 5 $0.00011 $0.00391
Haiku 4.5 $0.00006 $0.00196

Measured 5d ago against content hash fd4ec53b07a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

transformer 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 5d 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.

skills/transformer/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

input = $ARGUMENTS

Resolve $input to a path; if missing, try ${CLAUDE_SKILL_DIR}/../$input/SKILL.md then ./.claude/skills/$input/SKILL.md — if none resolve, ask. Read completely. Rewrite in place — diff is the review surface.

Rewrite, don't nibble. The default failure of this skill is timidity: touching the lines that are safe to touch and leaving the frame that was wrong. You have the whole file and a clear standard, so use them. Blank the file and rewrite from the skill's purpose when the structure is wrong, the frame is wrong, or the accumulated edits no longer add up to one coherent document — that is the expected outcome, not the escalation. Split one file into a tree, collapse a tree into one file, replace a procedure with a principle, invent a section the original lacked, delete half of it. A diff that is only nits means you read for typos instead of for design. The one place restraint is right: the load-bearing surfaces listed below, which survive verbatim through any rewrite.

The one test

For every line: what wrong behavior happens if this is gone? Wrong output, skipped coordination, lost trigger, silent regression → keep. Model arrives here unaided → strip.

Second test, for what survives: is this particular to this user, team, or product? A skill earns its keep by encoding opinion, taste, or a gotcha — generic good practice is the thing being cut.

Opus 5 is not a de-prescribe-everything migration — it runs prior-generation prompts well out of the box. The wins are targeted, and they cut both ways:

  • Compounding instructions — lines that duplicate a now-native behavior (verify, re-check, delegate, default-to-tool) don't just waste tokens, they push the model past the right amount of it. Strip.
  • Amplified defaults — length, narration, subagent appetite, scope creep, correction chatter all run hotter than on prior Opus models. Calibration against these is load-bearing; add it where the skill is silent.

Length is a side effect, not a target — "nothing to cut, much to add" is a valid verdict; removing more than adding ≠ automatically better. Apply strip/keep lists, base tendencies, effort guidance from the inlined reference below.

Read the full file on GitHub · 97 lines

Files

What ships with it

2 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. 5d ago First seen · 97 lines · 57 tokens per session scan A fd4ec53b07a3

Subscribe to this mod's changes

transformer is a skill published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 57 tokens to every session and 1,957 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 2026-08-31.