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 skills add mlopscommunity/Coding-Agents-Conference-skills --skill documentation-first-setupgit clone --depth 1 https://github.com/mlopscommunity/Coding-Agents-Conference-skillsWrote 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/skills/mlopscommunity/coding-agents-conference-skills/documentation-first-setup)<a href="https://agentmods.dev/skills/mlopscommunity/coding-agents-conference-skills/documentation-first-setup"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/documentation-first-setup/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/skills/mlopscommunity/coding-agents-conference-skills/documentation-first-setup"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/documentation-first-setup.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 | $0.00038 | $0.03309 |
| Opus 5.5 | $0.00015 | $0.01324 |
| Sonnet 5.5 | $0.00008 | $0.00662 |
| Haiku 4.5 | $0.00004 | $0.00331 |
Grade A, and why
documentation-first-setup 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 2mo 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 — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation-First Setup
Overview
The Documentation-First Setup Skill creates and maintains comprehensive documentation that helps agents navigate code effectively. Agents navigate codebases via semantic search and tree-walking. Without good docs, they get lost, make assumptions, and produce lower-quality work. Humans traditionally don't maintain documentation because it's tedious. But agents should do it—their time is cheaper than ours.
Core principle: Well-documented code lets agents navigate independently and make architecture-aware decisions. Poorly documented code makes agents ask basic questions instead of shipping features.
Dependency: Claude Code CLI with access to read files and create documentation.
When to Use
- New project setup: Establish documentation foundations from day one
- Onboarding new agents: Before assigning complex tasks
- After significant refactors: Update documentation to reflect new structure
- Before parallel work: Ensure agents have clear understanding of architecture
- Code review time: When you notice agents are confused about how things work
- Quarterly maintenance: Refresh documentation to match current codebase state
When NOT to Use
- Small, trivial projects (single file, obvious structure)
- When nobody will ever touch the code again
- For third-party or generated code (document around it, not within it)
Common Mistakes
| Mistake | Why it's wrong |
|---|---|
| Over-documenting obvious things | "The User class represents a user" wastes time. Focus on why and how, not what. |
| Not documenting design decisions | Agents and humans both ask "why is this structured this way?" Design decisions are the most valuable documentation. |
| Letting documentation drift | Docs that don't match code become lies. Update docs as part of code changes, not later. |
| Making READMEs longer than code | If your README is longer than the code, you're documenting the wrong things. |
| Orphaning cross-references | If A mentions B, B should mention A. If links are broken, documentation becomes useless. |
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.
- 2mo ago First seen · 443 lines · 38 tokens per session scan A e70f382b22e0
documentation-first-setup is a skill published in the GitHub repository mlopscommunity/Coding-Agents-Conference-skills (39 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 3,309 once invoked, about $0.0002 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.
documentation-first-setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| documentation-first-setupmlopscommunity/Coding-Agents-Conference-skills | Skill | 39 | 7mo ago | Apache-2.0 | A | 38 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 5d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 316k | 8d ago | MIT | A | 21 | Claude Code |