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 agentmods add commands/activecampaign/activecampaign-plugin/weekly-digestgit clone --depth 1 https://github.com/ActiveCampaign/activecampaign-pluginWhat 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 | $0.00019 | $0.00776 |
| Opus 5 | $0.00010 | $0.00388 |
| Sonnet 5 | $0.00004 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
weekly-digest 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 2d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/weekly-digest
Generate a weekly marketing digest summarizing activity across campaigns, automations, contacts, and deals.
Instructions
When the user runs /weekly-digest, produce a comprehensive weekly summary of their ActiveCampaign activity.
Server rule: The MCP server does not compute aggregates or totals. Report the counts and per-record numbers the tools return. Do not sum deal values into a "total pipeline value", average campaign rates, or tally "contacts completed this week" by paging the whole dataset. Where you can only show records (not a total), show the records and say so. Point users to AC's native reporting for true roll-ups.
Steps
-
Campaign activity: Use
list_campaignsto find campaigns sent in the last 7 days. For a notable one, useget_campaignto read its returned counts. Show each campaign's own numbers — don't blend them. -
Automation activity: Use
list_automationsto list active automations and the entered/completed counts carried on each record. -
Contact growth: Use
list_contactswith date filters to find contacts added in the last 7 days (show the count the query returns / the records). Uselist_listsfor list names and the subscriber counts the API returns per list. -
Deal activity: Use
list_dealsfiltered by status and date to show deals created / won / lost in the window as records, sorted by value where useful. Uselist_deal_pipelines/list_deal_stagesfor pipeline context. Do not total the values — list the deals. -
Present the digest in this format:
## Weekly Marketing Digest
**Week of [Date Range]**
---
### Campaigns Sent ([N] this week)
| Campaign | Date | Sends | Opens | Clicks |
|----------|------|-------|-------|--------|
| ... | ... | ... | ... | ... |
(Counts as returned by the API. Include a rate column only if the API returned it.)
**Most opens/clicks this week**: [Campaign Name]
---
### Automations
- **Active automations**: [N]
- Notable per-automation movement this week (from the records): [e.g. "Welcome series — 40 entered"]
---
### Contacts
- **New contacts this week**: [N returned by the dated query]
- **Lists**: [list name — subscriber count as returned], …
---
### Deals (last 7 days)
| Deal | Status | Value | Stage |
|------|--------|-------|-------|
| ... | won/open/lost | [as returned] | ... |
(Individual deals — not summed. For total pipeline value, see AC's native deal reporting.)
---
### Key Takeaways
1. [Most notable thing that happened, grounded in the records above]
2. [Area worth attention]
3. [Suggested action for next week]
### Not measured here
- Totals, averages, and blended rates aren't available via MCP — see AC's native reporting.
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.
- 2d ago First seen · 81 lines · 19 tokens per session scan A 46e4d734c73e
weekly-digest is a command published in the GitHub repository ActiveCampaign/activecampaign-plugin (0 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 776 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
feature
Post a feature to the Features Board on production and write tweets.
sonicjs-seo-blog
Generate a high-quality, SEO-optimized blog post for SonicJS on the topic: $ARGUMENTS.
seo-geo
SEO/GEO end-to-end along the SITE loop: survey demand and competitors, implement content, tune quality/tech/on-page, and evaluate authority/rankings/reports/memory (--phase survey|implement|tune|evaluate). Not sure? Use /aaron-marketing:auto.
email-audit
Full-spectrum email audit — technical rendering issues (Phase 1, Email Designer) and copy/strategy critique (Phase 2, Email Copywriter). Accepts pasted HTML or a description of an existing email.
competitive-landscape-analyzer
Comprehensive competitive analysis combining deep research with ad platform data. Includes competitor profiling, positioning maps, spend estimation, creative analysis, and strategic recommendations. Integrates Google Ads auction insights and Meta Ad Library research. (requires Pro subscription).
client-report
Produce the full client-facing first-scan pitch report for a prospect, end to end — live scan, research pass, branded PDF.