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 closing-plangit 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/closing-plan)<a href="https://agentmods.dev/skills/doris-labs/sales-skills/closing-plan"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/closing-plan/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/closing-plan"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/closing-plan.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 | $0.01466 |
| Opus 5.5 | $0.00028 | $0.00586 |
| Sonnet 5.5 | $0.00014 | $0.00293 |
| Haiku 4.5 | $0.00007 | $0.00147 |
Grade A, and why
closing-plan 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Closing Plan
Purpose
Turn a "we want to move forward" into a dated, owned, gate-by-gate plan that gets the contract signed by a real date — surfacing procurement, legal, and security blockers early instead of in the final week.
Inputs
- The target close date (the buyer's, not your forecast wish)
- The deal's current stage and what still has to happen to advance
- Open commitments on both sides and who owns them
- Known stakeholders, especially economic buyer, procurement, legal, and security
- The buyer's actual signing process (who signs, in what order, on what paper)
Method
- Map steps-to-signature, backward from the date. Start at "contract signed" and work back. Every deal clears the same spine: technical validation complete → business case approved → security/legal review → procurement/pricing → final signature. List the real steps for this deal in order, not a generic funnel.
- Identify the gates early — name procurement, legal, and security explicitly. These are the schedule killers. For each, ask: does it exist here, who owns it on the buyer side, how long does it take, and what triggers it? Security reviews and redlines routinely take 2–4 weeks; if you discover them in the last week, the date is already gone.
- Time-box every ask with a date. Each step gets
owner + action + by-date. Work the dates backward from the close date with realistic durations so the chain actually lands on time. A step without a date is a wish, not a plan. - Build a contingency for every gate that can slip. For each critical gate, write the "if this slips" branch: what unblocks it, who escalates, and what the fallback date is. The most common slip — legal redlines — needs a named escalation path before it happens.
- Confirm the buyer's actual signing process. Don't assume. Ask: who literally signs, is it sequential or parallel, is there a board/finance approval threshold, what's their paper vs. yours, and is there a PO or vendor-onboarding step after signature? The "last mile" after verbal yes is where deals die.
- Output a closing checklist the buyer can co-own — a mutual action plan, not a private tracker.
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 · 111 lines · 70 tokens per session scan A 357a4347ab9f
closing-plan is a skill published in the GitHub repository Doris-Labs/sales-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 70 tokens to every session and 1,466 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.
closing-plan compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| closing-planDoris-Labs/sales-skills | Skill | 3 | 5mo ago | MIT | A | 70 | 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 |