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.
git clone --depth 1 https://github.com/OPTIMETA/PAIDEIAWrote 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.
[](https://agentmods.dev/commands/optimeta/paideia/derive)<a href="https://agentmods.dev/commands/optimeta/paideia/derive"><img src="https://agentmods.dev/badge/commands/optimeta/paideia/derive/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.
<a href="https://agentmods.dev/commands/optimeta/paideia/derive"><img src="https://agentmods.dev/badge/commands/optimeta/paideia/derive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00034 | $0.00632 |
| Opus 5.5 | $0.00014 | $0.00253 |
| Sonnet 5.5 | $0.00007 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
derive 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Output language
Read INTERFACE_LANG from .course-meta (default en). All user-facing prose — chat output and narrative sections of the generated derivation MD — must be in that language. Keep in English regardless: file paths, slash command names, pattern IDs, LaTeX, and any literal section anchors downstream tools regex on.
Load skills/course-builder/SKILL.md for material locations. Also read course-index/summary.md to resolve the target.
Target: $ARGUMENTS
Procedure:
- Locate the derivation in
converted/textbook/*.mdandconverted/lectures/*.md. If present in both, prefer the textbook (usually cleaner). - If not in materials, derive it from first principles using standard techniques for the course's domain. Cite which earlier results you're using.
- Format as a clean reference markdown file with:
- Starting definitions/assumptions clearly stated
- Each step with a one-line explanation of why
- Boxed final result
- Short physical / mathematical interpretation at the end
- Typical pitfalls (common student errors) listed at bottom
- Save to
derivations/<slug>.md. Slug is lowercase-hyphenated from the target name. - Print (in $INTERFACE_LANG): "Saved
derivations/<slug>.md. Open and read; ask if any step is unclear."
Do NOT quiz or prompt the user — this command is a pure reference-writer. The user explicitly set this up so they can read rather than type.
Format convention (align with existing derivations/ files if any)
The skeleton below uses English labels; if INTERFACE_LANG=ko, translate the bold labels ("Goal", "Starting point", "Step 1 — ...", "Result", "Interpretation", "Pitfalls", "Reference") to natural Korean equivalents. Keep LaTeX, file paths, and equation content unchanged.
# <Target name>
**Goal.** <statement of what we want to derive>
**Starting point.** <definition / law / axiom / earlier result>
---
### Step 1 — <step description>
$$<step equation>$$
<why this step>
### Step 2 — ...
...
---
**Result.**
$$\boxed{\;<final>\;}$$
**Interpretation.** <1-2 sentences on what this means physically/mathematically>
**Pitfalls.**
- <common error 1>
- <common error 2>
**Reference.** <source section in converted/>
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.
- 1mo ago First seen · 67 lines · 34 tokens per session scan A 39e7cf5d32fd
derive is a command published in the GitHub repository OPTIMETA/PAIDEIA (92 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 632 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.
Other commands, from other repositories
openehr-explain
One-stop router that explains or looks up any openEHR thing — auto-detects an archetype, a template, an RM/AM/BASE type, an RM structural concept, an ADL idiom, an AQL query or keyword, or a terminology code (replaces /archetype-explain, /template-explain, /type-spec, /rm-structure, /adl-idiom, /terminology).
notebook
Draft and execute the paired notebook for a chapter (separable from prose drafting).
proof
Develop or verify mathematical proofs.
design-tutorial
Interactive guided tour of Naksha — learn commands through real exercises, discover workflows, and get oriented in under 10 minutes.
naksha-help
Quick-reference for any Naksha command — browse by category or look up a specific command.
b-animate-dev
Animate and model-check a B machine with probcli.