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 alebgl77/claude-inc --skill run-campaigngit clone --depth 1 https://github.com/alebgl77/claude-incWrote 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/alebgl77/claude-inc/run-campaign)<a href="https://agentmods.dev/skills/alebgl77/claude-inc/run-campaign"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/run-campaign.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.01230 |
| Opus 5 | $0.00000 | $0.00615 |
| Sonnet 5 | $0.00000 | $0.00246 |
| Haiku 4.5 | $0.00000 | $0.00123 |
Grade A, and why
run-campaign 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Campaign — Campaign Runner
"Run a campaign."
Seven days, one offer, channels the owner already controls. No ad account required, no agency, no month of planning.
When to use
- "We need sales this month" / "August is looking empty."
- "Run a promo for the shop" — seasonal push, anniversary, slow-season filler.
- "I have 900 emails and an Instagram — do something with them."
- Launching a new product or service to the existing customer base.
- Overstock, expiring inventory, or unbooked capacity that needs a deadline.
Workflow
- Nail the offer. One offer: the value (what they get and what it's worth), the deadline (day 7, a real date), and the reason-why (anniversary, season, slots to fill, overstock). No fake urgency — the owner must be able to say the reason with a straight face.
- Inventory owned channels. Email list size, each social account and its real reach, storefront traffic, partners who'd share. Pick 2–3 that can actually deliver; skip paid unless the user names a budget.
- Set the goal and do the math. One number (sales, bookings, covers). Back into required leads with a stated conversion assumption — compute it, write it down, judge day 8 against it.
- Build the day-by-day calendar. Tease → launch → proof → reminder → last call, mapped to real dates and the picked channels, respecting the list's tolerance (max three emails in seven days).
- Draft every asset. Three emails (launch, reminder, last call), three social posts (tease, proof, last call), flyer or counter-card copy. One voice, one offer, one CTA everywhere — same link, same code.
- Build the tracking sheet. Date, channel, spend, leads, sales, revenue, note. Two minutes a day to fill; it is the only reporting.
- Schedule the day-8 debrief. Goal vs actual, cost per sale, which channel pulled, keep / change / kill — and the date of the next campaign while the lessons are warm.
Output format
7-DAY CAMPAIGN KIT — <business> — starts <date>
OFFER
Value: <what they get and what it's worth>
Deadline: <day-7 date>
Reason-why: <the honest reason this deal exists>
Goal: <n> <sales/bookings> → needs ~<n> leads at <x>% assumed conversion
CHANNELS (owned)
1. <channel> — reach <n> — role: workhorse
2. <channel> — reach <n> — role: support
CALENDAR
D1 <date> | Tease post (<channel>) — hint, no link yet
D2 <date> | Launch email + post — full offer, one CTA
D3 <date> | Proof post — testimonial or photo, deadline restated
D4 <date> | Storefront/partner push — flyer up, partner shares
D5 <date> | Reminder email — handle the main objection, deadline visible
D6 <date> | Human-angle post — behind the scenes, soft CTA
D7 <date> | Last call — email at 9:00, post at 12:00 — hours left
ASSETS (full drafts follow)
Email 1 — Launch: <subject> + body
Email 2 — Reminder: <subject> + body
Email 3 — Last call: <subject> + body
Post 1 — Tease | Post 2 — Proof | Post 3 — Last call
Flyer: headline, three lines, CTA + <code/link>
TRACKING SHEET
Date | Channel | Spend | Leads | Sales | Revenue | Note
DAY-8 DEBRIEF (fill on <date>)
Goal vs actual | Cost per sale | Channel that pulled | Keep / Change / Kill | Next campaign date
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 First seen · 82 lines · 0 tokens per session scan A a3d7cb2c9f19
run-campaign is a skill published in the GitHub repository alebgl77/claude-inc (14 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,230 tokens. 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 2026-08-30.
Other skills, from other repositories
snack-batching
Weekly snack-request batching for {{officechannel}}. Collects Slack shortcut submissions since the last order, consolidates duplicates and standing staples, builds a cart against {{preferredvendor}} within {{weeklybudget}}, and posts it for the office manager to approve before anything is placed.
parcel-tracking
Track parcels and check delivery status for Australian and international couriers. Searches Gmail for dispatch/shipping emails and provides tracking links for all major Australian couriers including AusPost, StarTrack, Aramex, CouriersPlease, Sendle, Toll, Team Global Express, DHL, FedEx, TNT, Hunter Express, Border…
mcp-lark
Based on FeiShu(飞书) / Lark's OpenAPI MCP server, manage user information, chats, emails, cloud documents, multidimensional tables, tasks, calendars, etc.
maishou
A price-comparison workflow for products sold through major Chinese online marketplaces. It searches listings and can retrieve product details, purchase links, and available coupons.
giasip-dispatch
A skill for sending a task to other AI models and collecting their results. It supports direct API calls, command-line tools and built-in internal agents, depending on the model.
checklist
Activate when: user says 'let's make sure we don't skip anything', 'we need a pre-flight', 'build me a checklist for X', 'we keep missing steps in our deployment / close / launch', 'Gawande / Pronovost / checklist manifesto'. Do NOT activate when: the task is simple and one-off with no recurrence; the user is asking…