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.
npx agentmods add commands/danielpodolsky/ownyourcode/themegit clone --depth 1 https://github.com/DanielPodolsky/ownyourcodeWhat 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 | $0.00028 | $0.02508 |
| Opus 5 | $0.00014 | $0.01254 |
| Sonnet 5 | $0.00006 | $0.00502 |
| Haiku 4.5 | $0.00003 | $0.00251 |
Grade A, and why
theme 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 yesterday.
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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/own:theme
⚠️ PLAN MODE WARNING: Toggle plan mode off before running this command (
shift+tab). OwnYourCode commands don't work correctly with plan mode.
Restyle your project dashboard. The dashboard is self-styled — its CSS lives
inline in dashboard.html. This command re-cooks that inline <style> block
(and the Google-Fonts <link>) from your design brief, using the
frontend-design plugin when you have it, otherwise Claude's own design skills.
Overview
- View the current design brief
- Change the brief (free-text design description) → regenerate
- Regenerate from the existing brief (re-roll the look)
- Revert to a previous design via
/own:theme --revert
Files affected
ownyourcode/.theme/theme-prompt.md— the active design brief (you edit this)ownyourcode/dashboard/dashboard.html— its<style>block + font<link>are regeneratedownyourcode/.theme/.history/[ISO-timestamp]/— backup of the priordashboard.html+theme-prompt.md(created on every write; enables revert).claude/ownyourcode-manifest.json—theme.system,theme.last_updated
Hard constraints
- Visual only. Restyle, never restructure. The dashboard's render JS expects
a fixed set of class names and the
window.PROJECTcontract — NEVER rename, remove, or add classes, change the HTML structure, or touch the<script>blocks. If a brief asks for layout/behavior/data changes, refuse those parts and warn. - Never touch
dashboard-data.js. That's project content, not styling. file://rules: CSS stays inline (no external stylesheet<link>); web fonts via<link>in<head>are fine (the page is always online).- Backup-before-write is non-negotiable. Copy the current
dashboard.html+theme-prompt.mdto.history/[timestamp]/BEFORE regenerating.
Execution Flow
Phase 0: Argument detection
/own:theme --revert→ jump to Revert Flow below/own:theme(no args) → continue to Phase 1
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.
- yesterday First seen · 254 lines · 28 tokens per session scan A bd5a27f68ee4
theme is a command published in the GitHub repository DanielPodolsky/ownyourcode (276 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 2,508 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.
Other commands, from other repositories
project
Generate project documentation (product.md, structure.md, tech.md, codemaps/).
version
Display current guide and Claude Code versions.
toh-help
Display all Toh Framework commands and quick usage guide.
diff-docs
Compare official Anthropic docs baseline vs current snapshot (no network — instant).
update-workflow
Regenerate an existing custom workflow's shortcut command wiring from the current swarm template.
start
Start Forge Mentor in this project — connect accounts, agree permissions, and begin the foundation interrogation.