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 Doris-Labs/sales-skills --skill demo-strategygit clone --depth 1 https://github.com/Doris-Labs/sales-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/doris-labs/sales-skills/demo-strategy)<a href="https://agentmods.dev/skills/doris-labs/sales-skills/demo-strategy"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/demo-strategy/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/doris-labs/sales-skills/demo-strategy"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/demo-strategy.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 | $0.01317 |
| Opus 5.5 | $0.00025 | $0.00527 |
| Sonnet 5.5 | $0.00013 | $0.00263 |
| Haiku 4.5 | $0.00006 | $0.00132 |
Grade A, and why
demo-strategy 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 2mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demo Strategy
Purpose
Turn discovery into a demo plan that shows only what maps to a named pain, lands one memorable wow moment, and speaks to each role in the room — ending in a concrete demo flow you can run from.
Inputs
- The pains discovered so far (and whose pain each is)
- Who will be in the room and their role / what they care about
- The product capabilities available to show
- The deal's current stage and what this demo needs to advance
Method
- Discovery-driven selection. List every feature you're tempted to show. Beside each, write the named pain it answers and the person who voiced it. If a feature has no named pain next to it, cut it. A demo is not a feature tour — it's proof you listened. Default to showing fewer things, deeper.
- Tell-show-tell each segment. For every feature that survives the cut, structure
it in three beats:
- Tell: restate the pain in their words ("You said reps lose 2 hours a day re-typing call notes into the CRM…").
- Show: the smallest live path that proves you solve it. No menu tours, no "and you can also…". One clean path to the payoff.
- Tell: the "so what." (see next step.)
- "So what / why it matters" line per feature. Every feature shown gets one
sentence that converts capability into outcome, in business terms:
Because <feature>, you <outcome that maps to the pain> — which means <impact on their metric / their day>.If you can't write this line, you don't yet know why to show the feature. - Plan one wow moment. Pick a single beat to land as the demo's peak — the thing they'll repeat to whoever wasn't in the room. It should hit the most expensive or most emotional pain, be live (not a slide), and feel effortless. Sequence the demo so this moment arrives after you've earned trust but before attention fades — not the very first thing, not buried at the end.
- Tailor to the audience in the room. Map what each role needs to see:
- End user / champion: does it make their day easier? Show the daily workflow.
- Economic buyer: does it move a number they own? Lead with outcome, keep it short.
- Technical evaluator: does it fit / integrate / secure? Be ready to go deeper. Order segments so each person hears their pain answered. If the room is mixed, open with the economic buyer's outcome, then go deep for the user/technical seats.
- Output the demo flow. Produce a per-segment plan:
pain → feature → outcome, tagged with which audience segment it's for, and the wow moment marked.
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.
- 2mo ago First seen · 106 lines · 63 tokens per session scan A bc7d704840af
demo-strategy is a skill published in the GitHub repository Doris-Labs/sales-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 63 tokens to every session and 1,317 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.
demo-strategy compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| demo-strategyDoris-Labs/sales-skills | Skill | 3 | 5mo ago | MIT | A | 63 | Claude Code |
| lynquGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 40 | Claude Code, Codex |
| lynqu-sales-followupGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 39 | Claude Code, Codex |
| lynqu-deal-deskGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 48 | Claude Code, Codex |
| lynqu-event-blitzGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 47 | Claude Code, Codex |
| lynqu-lead-managementGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 40 | Claude Code, Codex |
| lynqu-outreachGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 41 | Claude Code, Codex |