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 beachhead-segmentgit 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/beachhead-segment)<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/beachhead-segment"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/beachhead-segment/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/beachhead-segment"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/beachhead-segment.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 | $0.00065 | $0.04565 |
| Opus 5.5 | $0.00026 | $0.01826 |
| Sonnet 5.5 | $0.00013 | $0.00913 |
| Haiku 4.5 | $0.00006 | $0.00456 |
Grade A, and why
beachhead-segment 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 13d 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 — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beachhead-Segment — Skill
How This Works
Identifies the highest-probability segment to dominate first — before expanding. This is the wedge. Everything else (positioning, GTM strategy, proof points) follows from getting this right.
The skill runs in 7 steps:
Step 0 — Load brain context (ICP, positioning, competitive landscape, proof points) and, if the user maintains /context/meta-patterns.md, guardrails logged there.
Step 1 — Identify candidates: Name 2–5 segments or ask user to decompose current ICP.
Step 2 — Score each segment on four dimensions: Burning Pain, Willingness to Pay, Winnability, Referral Potential.
Step 3 — Apply blocking gates: Pain floor (≥3), Winnability floor (≥3), assumption density check.
Step 4 — Recommend beachhead with expansion pathway, 90-day activation plan, and specific rejection reasons for every eliminated segment.
Step 5 — Update brain Section 2 with confirmed beachhead (on user confirmation).
Step 6 — Learning Close: log the session to /context/skill-sessions.md.
Correction (2026-08-24): this summary previously listed 8 entries (Step 0 through Step 7) under "runs in 7 steps," and named a standalone "Step 5 — Pressure-test eliminated segments" that never existed as its own section in the body — the body always went straight from Step 4 (Recommend) to what it labeled Step 5 (Update Brain). Rejection reasons for eliminated segments were already produced inside Step 4's own output template ("Why not Segment B/C" lines and the Eliminated Segments table) — that was real, just mislabeled as a separate step. The step count and numbering above now match the body exactly: 7 steps, numbered 0–6.
Trigger
- When: Choosing which customer segment to focus on first, before scaling GTM investment across multiple segments at once — narrowing a broad ICP down to the first wedge.
- Not for: Full ICP definition from scratch → use
product-marketing-context. Launch tier assignment once the beachhead is already confirmed → usego-to-market-strategy. Mapping the buying committee inside a confirmed beachhead → usebuyer-personas. Messaging for a confirmed beachhead → usepositioning-messaging. - Example prompts:
- "Which segment should we focus on first?"
- "Our ICP is too broad — help me narrow it"
- "Pick a beachhead for us"
- "Where do we win first?"
- "What's our wedge?"
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.
- 13d ago Changed · +3 lines · -22 tokens per session 7b6f2c9e5154
- 21d ago Changed 2d8ea5251446
- 22d ago Changed bc283e0ecf14
- 28d ago Changed · +13 lines 3e4b2be7740b
- 1mo ago Changed · -1 tokens per session f96fa1a1b6b5
- 1mo ago Changed · +2 lines b5eb634115c6
- 2mo ago First seen · 423 lines · 88 tokens per session scan A 88949a747837
beachhead-segment is a skill published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (8 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 4,565 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 2026-08-31.
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.