A command for creating a new practice problem based on a known hardware or example problem while keeping the same solving method. The learner solves the new problem on paper, uploads a PDF, and uses another command to grade it.

Use it to generate a variant of a known problem, save its problem and hidden solution files, and receive instructions for submitting the handwritten solution.

It provides fresh practice without changing the underlying technique being learned. This helps check whether the learner can apply a method to different values or wording.

twin — Command by OPTIMETA

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 commands/optimeta/paideia/twin

Clone the repo

git clone --depth 1 https://github.com/OPTIMETA/PAIDEIA

Or install paideia, the plugin that ships this one along with the rest of its 6 skills, 18 commands.

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 481 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.

Model	Per session	Once invoked
Fable 5	$0.00029	$0.00481
Opus 5	$0.00015	$0.00241
Sonnet 5	$0.00006	$0.00096
Haiku 4.5	$0.00003	$0.00048

Measured 3d ago against content hash ba7238e56199, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

twin 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 3d 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.

plugins/paideia/commands/twin.md · 40 lines

What it actually says

Output language

Read INTERFACE_LANG from .course-meta (default en). All user-facing prose must be in that language. Keep in English regardless: file paths, slash command names, pattern IDs, LaTeX, and YAML keys.

Load skills/exam-drill/SKILL.md and skills/exam-drill/twin-recipe.md. Read course-index/patterns.md.

Target: $ARGUMENTS

Procedure:

Locate original. Search converted/homework/ and converted/solutions/ for the problem-id. If not found, also check converted/lectures/*.md and converted/textbook/*.md for worked examples.
Identify pattern(s) used. Cross-reference with course-index/patterns.md.
Apply twin-recipe.md rules. Hold pattern, topic, step count invariant. Vary system, numbers, names, direction.
Save two files:
- Problem → twins/<id>_<ts>.md
- Solution → twins/<id>_<ts>_sol.md (hidden)
Print to chat (in $INTERFACE_LANG):
- The twin problem statement (do NOT reference the original problem ID in the output)
- Instruction: "Solve on paper, upload as answers/twin_<id>_<ts>.pdf, then /grade. Or just describe the strategy in 3–5 lines."
If user responds with strategy text (not PDF):
- Match 3 axes: pattern / variable-choice / end-form
- If all ✅: confirm, optionally copy the sol.md content into derivations/twin-<id>.md
- If any ❌: flag specifically, ask for revision
Quality check before presenting:
- ✅ Pattern genuinely required
- ✅ Answer differs from original
- ✅ Origin problem ID not leaked
- ✅ Well-posed

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.

3d ago First seen · 40 lines · 29 tokens per session scan A ba7238e56199

Subscribe to this mod's changes

twin is a command published in the GitHub repository OPTIMETA/PAIDEIA (91 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 481 once invoked, about $0.0001 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.

Learning and teaching claude-code claude-code-plugin engineering exam-prep local-first markdown

fieldtheory

Explain and drive the Field Theory CLI — bookmark-sourced seeds, repo-aware possibility runs that score ideas onto a 2x2 grid, and the interconnected .md files they leave behind. Trigger when the user asks about ft, bookmarks, seeds, ft possible (or the older name ft ideas), grids, dots/nodes, or how to turn saved…

afar1/fieldtheory-cli · 88 tokens

twin

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Output language

What this file has done since we first saw it

Other commands, from other repositories

fieldtheory

book-characters

learn

tree

repo-overview

OPSX: Onboard