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 positioning-ideasgit 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/positioning-ideas)<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/positioning-ideas"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/positioning-ideas/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/positioning-ideas"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/positioning-ideas.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 | $0.00058 | $0.03000 |
| Opus 5.5 | $0.00023 | $0.01200 |
| Sonnet 5.5 | $0.00012 | $0.00600 |
| Haiku 4.5 | $0.00006 | $0.00300 |
Grade A, and why
positioning-ideas 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 8d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Positioning Ideas
How This Works
positioning-messaging BUILD mode produces one finished, gated
positioning statement — that's deliberate, since shipping copy needs a
7-point verification gate behind it. But choosing a direction in the
first place is a different job: before committing to one statement, it's
often more useful to see 3-5 genuinely different angles side by side,
each opening different unclaimed territory, and pick (or blend) one.
This skill exists for that moment only — divergent, ungated, disposable
brainstorm output. It writes nothing durable and produces no shippable
copy on its own. Every option it hands back must be run through
positioning-messaging's BUILD mode and its gate before it becomes real
positioning copy — this skill explicitly does not replace that gate, it
feeds it.
Step 0 — Load brain Section 1 (Product), Section 2 (ICP), and Section 3 (Alternatives & Positioning). If Section 3 has fewer than 3 named alternatives including status quo, or there is no brain, run the Quick-Brain from Pre-flight first, since divergent positioning options are meaningless without knowing what's actually being differentiated from.
Step 1 — Confirm the target segment (from a recent beachhead-segment
or buyer-personas session if one exists, or ask directly).
Step 2 — For each named alternative in Section 3, identify the specific unclaimed territory it leaves open — the thing that alternative structurally can't claim, not a generic "we're better" gap.
Step 3 — Generate 3-5 divergent positioning statement options, each tied to a different alternative's gap, each including a positioning statement, strategic rationale, supporting message, and the specific competitive advantage that makes the claim credible.
Step 4 — Self-check for actual divergence — options that differ only in wording but claim the same territory get collapsed or flagged, not delivered as if they were distinct choices.
Step 5 — Learning Close: log the session to /context/skill-sessions.md,
and hand off explicitly to positioning-messaging BUILD mode for
whichever option (or blend) gets chosen.
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.
- 8d ago Changed · -1 lines · -8 tokens per session 768279847d98
- 16d ago Changed b4288a1e8db9
- 17d ago Changed · +16 lines 437c2ce54646
- 1mo ago Changed · +4 lines 0882d955f47d
- 1mo ago Changed f69e58a8a5bb
- 1mo ago Changed · +3 lines f11fc7b05bb7
- 1mo ago First seen · 259 lines · 66 tokens per session scan A 1d060926f7ba
positioning-ideas is a skill published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (8 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 3,000 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 2026-09-08.
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.