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 stefanoskarakasis/Product-Marketing-Skills --skill message-housegit clone --depth 1 https://github.com/stefanoskarakasis/Product-Marketing-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/stefanoskarakasis/product-marketing-skills/message-house)<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/message-house"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/message-house/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/stefanoskarakasis/product-marketing-skills/message-house"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/message-house.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 | $0.00061 | $0.03411 |
| Opus 5.5 | $0.00024 | $0.01364 |
| Sonnet 5.5 | $0.00012 | $0.00682 |
| Haiku 4.5 | $0.00006 | $0.00341 |
Grade A, and why
message-house 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 19d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
Use when the user asks to "build a message house," "put our messaging in a message house," "give me the roof and pillars," references messagehouse.org, or wants their positioning and value pillars laid out as a single scannable table for sales, leadership, or a new hire.
Not for: building positioning or a messaging hierarchy from scratch (route to positioning-messaging), building personas from scratch (route to buyer-personas), or sourcing a new proof point or stat (route to proof-points). This skill formats what already exists — it does not derive strategy.
Example prompts:
- "Build our message house"
- "Turn our positioning into a message house table"
- "I need the roof and pillars for a new hire deck"
Inputs
- Product/company name (if not resolvable from brain Section 1)
- Optional: a pasted
positioning-messagingBUILD or AUDIT output from this session — takes precedence over stale brain content for the same field - Optional: number of pillars to build (default: however many the source material supports, capped at 3)
Brain Read/Write Contract
- Reads: Section 1 (Product context), Section 2 (ICP — for Target audience/User persona), Section 3 (Positioning), Section 4 (Voice and tone), Section 5 (Market context — for Customer pain), Section 6 (Proof points)
- Writes: none. This is a read-only, output-only formatter. It never edits
/foundation/brain.md. - Never writes to: any brain section.
Pre-flight
Load /foundation/brain.md if present. If absent, check whether the user has pasted a positioning-messaging output this session.
Gate check — block if both are missing:
"No brain and no positioning output found. A message house formats existing positioning — it doesn't create it. Paste your positioning statement and your key differentiators here and I'll format them, or run
positioning-messaging(BUILD mode) first, then come back."
Gate check — block if positioning is present but too thin: if Section 3 has no positioning statement and no named differentiators/pillars, do not proceed to Step 2. Surface the same prompt: paste the positioning here, or run positioning-messaging (BUILD mode) first.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 19d ago Changed 6a45593849ab
- 20d ago Changed · +1 lines db7f75b5b37a
- 25d ago Changed 4f98c2671b67
- 28d ago Changed · +1 lines 50d289117a8c
- 1mo ago Changed · +3 lines 326240b8bd4a
- 1mo ago Changed · +21 lines · -23 tokens per session d5c7676c7677
- 1mo ago First seen · 158 lines · 84 tokens per session scan A 2283c566d1a8
message-house is a skill published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (8 stars, last pushed 3d ago), licensed MIT. It adds 61 tokens to every session and 3,411 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 2026-09-16.
Other skills, from other repositories
report
A way to export a chat card or reply as a standalone HTML report, meaning a file that can open in a browser without the chat application. It preserves the card template, including right-to-left Persian or left-to-right English layouts.
k8s-rightsize
Right-size Kubernetes CPU and memory requests from Prometheus usage (p95 CPU, p98 memory over 7 days), size the node count, tune KEDA autoscaling. Use when asked to rightsize workloads, cut node cost, or "how many nodes do we need".
owasp-security
Deep OWASP reference: Top 10 2025, ASVS 5.0, secure patterns, per-language quirks, LLM Top 10 and agentic AI security. Use for an in-depth security review, auth work, or hardening an LLM or agent app. For the everyday baseline use secure-coding.
fig
One self-contained HTML file holding a looping animated SVG, for ideas that move: flows, loops, retries, queues, fan-outs. Use when the user says "fig" or a diagram would be better animated.
brand
A project-specific visual identity for chat cards and saved reports, using the project's colors, logo, and fonts. It finds these details in the repository or asks the user for them, then stores the result in a committable `.readable/` folder.
workspace-rules
A set of guidelines for deciding which rules belong in a repository's workspace instructions and which should be enforced by its build or checks.