Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/TrentM6/baseline-corenpx agentmods add skills/trentm6/baseline-core/technical-documentationWrote 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/trentm6/baseline-core/technical-documentation)<a href="https://agentmods.dev/skills/trentm6/baseline-core/technical-documentation"><img src="https://agentmods.dev/badge/skills/trentm6/baseline-core/technical-documentation/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/trentm6/baseline-core/technical-documentation"><img src="https://agentmods.dev/badge/skills/trentm6/baseline-core/technical-documentation.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 | $0.00033 | $0.02041 |
| Opus 5.5 | $0.00013 | $0.00816 |
| Sonnet 5.5 | $0.00007 | $0.00408 |
| Haiku 4.5 | $0.00003 | $0.00204 |
Grade A, and why
technical-documentation 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Documentation
Product documentation helps users understand, use, and troubleshoot products. Good documentation is clear, accurate, findable, and maintained. It reduces support burden and improves user success.
Core Principles
-
Write for the reader, not yourself. Documentation serves users. What do they need to know? What are they trying to do?
-
Accuracy is non-negotiable. Wrong documentation is worse than no documentation. Verify everything.
-
Show, don't just tell. Examples, screenshots, and code samples make abstract concepts concrete.
-
Scannable first, readable second. Users scan for answers. Make structure obvious. They'll read when they find the right section.
-
Maintenance is half the work. Outdated docs erode trust. Build in processes to keep docs current.
-
Link, don't repeat. Single source of truth. Link to authoritative content rather than duplicating.
-
Progressive disclosure. Start simple, go deep. Quick start first, advanced topics later.
Industry Principles
-
Task-oriented structure. Organize around what users want to do, not how the product is built.
-
Consistent terminology. Use the same words for the same things. Create a glossary if needed.
-
Accessible language. Clear, simple language. Avoid jargon unless defining it.
-
Visual hierarchy. Headers, lists, code blocks, callouts — structure helps navigation.
-
Test with real users. Can they complete tasks using your docs? If not, revise.
Workflow
Follow the Workflow Orchestration Pattern for the universal workflow approach. Below are the documentation-specific details for each step.
1. Clarify Before Starting
Before writing documentation, understand:
- Who is the audience? New user, power user, admin?
- What's the purpose? Learn a concept, complete a task, troubleshoot?
- What's the scope? Single feature, entire product, quick start?
- What format? Tutorial, reference, how-to, explanation?
- What exists already? Building on existing docs or starting fresh?
- Who maintains it? What's the update process?
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 · 295 lines · 33 tokens per session scan A 372cdac39591
technical-documentation is a skill published in the GitHub repository TrentM6/baseline-core (23 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 2,041 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 2026-11-17.
technical-documentation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| technical-documentationTrentM6/baseline-core | Skill | 23 | 2d ago | MIT | A | 33 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 108k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 37k | today | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 50k | today | MIT | A | 48 | Claude Code |
| report-to-pdfasgeirtj/system_prompts_leaks | Skill | 72k | today | CC0-1.0 | A | 17 | Claude Code, Codex |
| legal-holdanthropics/claude-for-legal | Skill | 10k | 2d ago | Apache-2.0 | A | 68 | Claude Code |
| artifact-template-minimal-letterheadasgeirtj/system_prompts_leaks | Skill | 72k | today | CC0-1.0 | A | 54 | Claude Code, Codex |