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/arome3/code-to-content/tutorialgit clone --depth 1 https://github.com/arome3/code-to-contentWhat 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 | $0.00010 | $0.00573 |
| Opus 5 | $0.00005 | $0.00287 |
| Sonnet 5 | $0.00002 | $0.00115 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
tutorial 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Technical Tutorial
Create a step-by-step tutorial that teaches developers how to use or build something from the provided project.
Differentiation Discovery (offer; never blocking): Before generating, offer to make this unmistakably theirs — ask for the WHY (the thesis/stakes), one defensible opinion, a road not taken, or a rough draft to polish ("write it ugly; I'll keep your voice"). Rank raw material (Slack threads, support tickets, a voice-memo transcript) above clean specs. If declined, proceed on code alone and flag
Distinctiveness: AT RISK. At delivery, run the swap-the-name test + AI-tells blocklist fromreferences/differentiation.md.
Process
-
Analyze the Project Analyze the codebase Claude-natively (read dependency files, detect architecture, grep story hooks like TODO/FIXME, mine
git log) — seereferences/analysis-prompts.md. No scripts required. -
Load Skill Context Read these files:
skills/code-to-content/SKILL.mdskills/code-to-content/references/differentiation.md(WHY / opinion / roads-not-taken)skills/code-to-content/references/formats.md(tutorials section)skills/code-to-content/assets/templates/tutorial.md
-
Identify Learning Objective Ask the user: What single skill should readers gain from this tutorial?
-
Structure the Tutorial Follow the 6-section structure:
- Hook & Outcome (what they'll build)
- Prerequisites (required knowledge, tools, time)
- Foundation (first 5 minutes - get something working)
- Build (one concept per section)
- Polish (error handling, production considerations)
- Next Steps (extensions, related topics)
-
Apply Progressive Disclosure
- Start with simplest working version
- Add complexity incrementally
- 5-9 numbered steps (one action per step)
- Checkpoint after each step
- Troubleshooting blocks for common errors
-
Validate Ensure content matches audience level using: Estimate readability Claude-natively against the audience thresholds in
references/readability-guide.md(grade level, jargon %, code:prose ratio).
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 · 54 lines · 10 tokens per session scan A e2239986daf7
tutorial is a command published in the GitHub repository arome3/code-to-content (6 stars, last pushed 2mo ago), licensed MIT. It adds 10 tokens to every session and 573 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 2026-08-31.
Other commands, from other repositories
retrospective
Perform a post-implementation retrospective analysis measuring spec adherence, implementation deviations, and lessons learned.
revise-claude-md
Update CLAUDE.md with learnings from this session.
protracted-strategy
用持久战略为长期复杂任务划分阶段、设置转折条件。.
resume_handoff
Resume work from handoff document with context analysis and validation.
distill
Distill important session insights into doc/loom/knowledge.
demo-command
Example slash command that wraps the demo-skill. Showcases the command kind.