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/product-communicationsWrote 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/product-communications)<a href="https://agentmods.dev/skills/trentm6/baseline-core/product-communications"><img src="https://agentmods.dev/badge/skills/trentm6/baseline-core/product-communications/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/product-communications"><img src="https://agentmods.dev/badge/skills/trentm6/baseline-core/product-communications.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 | $0.00037 | $0.03155 |
| Opus 5.5 | $0.00015 | $0.01262 |
| Sonnet 5.5 | $0.00007 | $0.00631 |
| Haiku 4.5 | $0.00004 | $0.00315 |
Grade A, and why
product-communications 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 — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Communications
Product communications is the discipline of writing documents that move work forward. PRDs, specs, briefs, and updates that align teams, capture decisions, and enable execution. Good product docs reduce meetings, prevent misalignment, and create shared understanding.
Core Principles
-
Write to decide, not to document. The best product docs force clarity and drive decisions. If a doc doesn't change anyone's thinking or behavior, it's not worth writing.
-
Audience determines format. Engineers need different detail than executives. A launch brief is not a PRD. Match the document to who's reading it and what they need.
-
Start with the why. Every doc should answer "why are we doing this?" before "what are we doing?" Context enables good judgment downstream.
-
Explicit over implicit. Assumptions, trade-offs, and out-of-scope items belong in the doc. What's not written will be assumed differently by everyone.
-
Living documents, not artifacts. Good docs evolve. Date your updates, note what changed, keep it current. Stale docs are worse than no docs.
-
Brevity is respect. People are busy. Say what needs to be said in as few words as possible. If you can cut a section, cut it.
-
Visuals when they help. A diagram can replace paragraphs. Use wireframes, flows, and tables when they communicate faster than prose.
Industry Principles
-
Separate problem from solution. The "why" and "what problem" should be solid before the "how." Don't let solution details obscure the problem being solved.
-
Success criteria are non-negotiable. Every feature needs a definition of success. "How will we know this worked?" must be answered.
-
Edge cases belong somewhere. Not every edge case goes in the main doc. But they need to be captured — in appendix, comments, or linked docs.
-
Async-first. Write docs that work without you in the room. If it requires your live explanation, it's not done.
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 · 477 lines · 37 tokens per session scan A 89de2d432d6c
product-communications is a skill published in the GitHub repository TrentM6/baseline-core (23 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 3,155 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.
product-communications compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| product-communicationsTrentM6/baseline-core | Skill | 23 | 2d ago | MIT | A | 37 | 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 |