automation-audit

automation-audit is a command for coding agents from ActiveCampaign/activecampaign-plugin. It costs 25 tokens per session (799 once invoked), scanned A, original, MIT.

A command for reviewing active automations, which are workflows that run actions automatically, and identifying ones that may need attention.

In plain words
What is it for?
Finding stale or disabled workflows, spotting possible drop-off from the counts shown on each automation, and producing recommendations.
Why use it?
It brings together each automation's status and recorded entered and completed counts without pretending to calculate unavailable account-wide rates.

Command

Part of the activecampaign plugin — 6 skills, 5 commands, 2 agents, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add commands/activecampaign/activecampaign-plugin/automation-audit
Clone the repo
git clone --depth 1 https://github.com/ActiveCampaign/activecampaign-plugin

Or install activecampaign, the plugin that ships this one along with the rest of its 6 skills, 5 commands, 2 agents, 1 MCP server.

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 799 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00799
Opus 5 $0.00013 $0.00400
Sonnet 5 $0.00005 $0.00160
Haiku 4.5 $0.00003 $0.00080

Measured 3d ago against content hash 55ccad533f72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

automation-audit 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 3d 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.

commands/automation-audit.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/automation-audit

Review automation performance and identify automations that need attention.

Instructions

When the user runs /automation-audit, analyze all active automations and surface issues, opportunities, and recommendations.

Server rule: The MCP server does not compute aggregates, so a true account-wide "completion rate" or "average duration" is not available. list_automations returns each automation's name, status, and the contact counts the API exposes on the record itself (e.g. entered / completed counts). Report those per-automation numbers as returned. Do not page through list_contact_automations for every contact to compute a rate yourself — that violates the server's rules and is what AC's native automation reporting is for. Frame "needs attention" qualitatively from the per-record numbers, not from a threshold you calculated across the dataset.

Steps

  1. Get all automations: Use list_automations to fetch automations and their status (active/disabled) plus whatever entered/completed counts the records carry. (One call per turn; follow next_page only to show more automations.)

  2. Read per-automation signals from the records themselves: For each automation, use the counts already present on the list_automations record — entered count, completed count, status. If the user wants detail on one specific automation, you may use list_contact_automations filtered to that automation to show individual run statuses — but describe them qualitatively, don't compute a fleet-wide percentage.

  3. Flag qualitatively (based only on the returned per-record numbers):

    • Automations where the record shows many entered but few completed — note as a possible drop-off to investigate in native reporting
    • Stale — active but the record shows little/no recent entry
    • No goals set — automations without a measurable outcome
    • Possible overlap — multiple automations that appear to target the same audience
  4. Present the audit in this format:

Read the full file on GitHub · 67 lines

Changes

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.

  1. 3d ago First seen · 67 lines · 25 tokens per session scan A 55ccad533f72

Subscribe to this mod's changes

automation-audit is a command published in the GitHub repository ActiveCampaign/activecampaign-plugin (0 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 799 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.