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/setupWrote 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/setup)<a href="https://agentmods.dev/skills/trentm6/baseline-core/setup"><img src="https://agentmods.dev/badge/skills/trentm6/baseline-core/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/trentm6/baseline-core/setup"><img src="https://agentmods.dev/badge/skills/trentm6/baseline-core/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 | $0.00063 | $0.03362 |
| Opus 5.5 | $0.00025 | $0.01345 |
| Sonnet 5.5 | $0.00013 | $0.00672 |
| Haiku 4.5 | $0.00006 | $0.00336 |
Grade A, and why
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 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup
Setup is how a freshly-scaffolded Baseline System learns who the user is. It runs once per system. Every other skill produces better output because of what setup captures.
The default path is doc-first: most users have written collateral already (pitch deck, one-pager, brand guide, product spec). Have them drop those in chat, parse what fits each context file, confirm with the user, write to disk. Then ask short gap-filling questions only for what the docs didn't cover. Users with no docs run a guided questionnaire instead — but with multiple-choice options where they make sense, not 80 cold open prompts.
Core Principles
-
Use what the user already has. A pitch deck answers half the identity questions for free. Don't ask a user to retype what they can paste.
-
Show drafts, don't just write. Before saving any context file, show the user the draft you extracted or composed and ask for confirmation. Edits are cheap when proposed; expensive when discovered later.
-
Ask fewer, sharper questions. A multiple-choice "what stage are you?" beats an open "describe your company stage." Always offer free-text fallback.
-
Voice is special — get a sample first. Asking "what's your voice?" cold produces useless answers. Ask for 2-3 samples of the user's existing writing and infer voice rules from them. See voice-elicitation.md.
-
Never block on missing context. If the user can't or won't answer something, write what you have and move on. Empty context produces more generic output, not broken output.
-
Stage-aware. A pre-launch company can't answer "what's your typical deal size." A growth-stage company doesn't need to redo positioning. Ask the user's stage first; skip questions that don't apply.
-
One pass per file. Don't loop back to identity.md after moving to product.md. If the user wants to revise, they can re-run setup or edit the file directly.
Workflow
Follow the Workflow Orchestration Pattern for the universal workflow approach. Below are the setup-specific details for each step.
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 · 258 lines · 63 tokens per session scan A eb58ee282a84
setup is a skill published in the GitHub repository TrentM6/baseline-core (23 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 3,362 once invoked, about $0.0003 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.
setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setupTrentM6/baseline-core | Skill | 23 | 2d ago | MIT | A | 63 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 136k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 101k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 14k | today | CC0-1.0 | A | 113 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |