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 gtm-skills/gtm --skill meddic-discovery-litegit clone --depth 1 https://github.com/gtm-skills/gtmWrote 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/gtm-skills/gtm/meddic-discovery-lite)<a href="https://agentmods.dev/skills/gtm-skills/gtm/meddic-discovery-lite"><img src="https://agentmods.dev/badge/skills/gtm-skills/gtm/meddic-discovery-lite/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/gtm-skills/gtm/meddic-discovery-lite"><img src="https://agentmods.dev/badge/skills/gtm-skills/gtm/meddic-discovery-lite.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 | $0.00070 | $0.01029 |
| Opus 5.5 | $0.00028 | $0.00412 |
| Sonnet 5.5 | $0.00014 | $0.00206 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
meddic-discovery-lite 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 22d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MEDDIC Discovery Lite
MEDDIC is six questions about whether a deal is real. This skill turns it into something you can run before a call (which questions to ask) and after (how qualified are we, and what is missing).
The six elements
| Letter | Element | The question it answers |
|---|---|---|
| M | Metrics | What measurable result does the buyer expect, and have they said the number? |
| E | Economic Buyer | Who can say yes with budget they control, and have we spoken to them? |
| D | Decision Criteria | What will they judge vendors on, in their words? |
| D | Decision Process | What steps, who, and by when? |
| I | Identify Pain | What breaks today, what does it cost, and who feels it? |
| C | Champion | Who inside wants this to happen, has influence, and will sell for us when we are not in the room? |
Question bank
Ask these as a conversation, not a checklist. Two or three per element is enough for a first call.
Metrics
- If this works, what number changes, and from what to what?
- How are you measuring that today?
- What would make this a clear win in six months?
Economic Buyer
- Who signs off on spend like this?
- Have they been part of the conversation yet?
- What do they care about that is different from what you care about?
Decision Criteria
- When you compare options, what matters most?
- Is there anything that would rule a vendor out immediately?
- Who else gets a vote on the criteria?
Decision Process
- Walk me through what happens between "we like it" and "it is live".
- Who needs to be involved — security, legal, procurement, IT?
- What is the date this needs to be working by, and what happens if it slips?
Identify Pain
- What is happening today that made you take this call?
- What does that cost you — time, money, people, missed targets?
- Who feels it most? What have you tried?
Champion
- Who inside is pushing for this?
- What do they gain personally if it ships?
- Would they introduce us to the economic buyer?
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.
- 22d ago First seen · 97 lines · 70 tokens per session scan A 265ea7fbde73
meddic-discovery-lite is a skill published in the GitHub repository gtm-skills/gtm (188 stars, last pushed 23d ago), licensed MIT. It adds 70 tokens to every session and 1,029 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 2026-10-15.
meddic-discovery-lite compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| meddic-discovery-litegtm-skills/gtm | Skill | 188 | 23d ago | MIT | A | 70 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |