preflight-campaign

preflight-campaign is a skill for Claude Code from katekruger/campaign-preflight. It costs 126 tokens per session (1,451 once invoked), scanned A, original, MIT.

A skill for checking an outbound email campaign before it is sent. It inspects campaign details and lead lists without activating, editing, or sending anything.

In plain words
What is it for?
It checks campaign files, pasted leads, or campaign descriptions and reports problems in plain language.
Why use it?
It finds issues that could cause unsafe, incorrect, or non-compliant emails to go out.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the campaign-preflight plugin — 3 skills, 1 MCP server shipped together

Good fit It checks campaign files, pasted leads, or campaign descriptions and reports problems in plain language.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add katekruger/campaign-preflight
Claude Code
/plugin install campaign-preflight

Made for: Claude Code.

Or install campaign-preflight, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

Wrote 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.

agentmods badge for preflight-campaign

README.md
[![agentmods](https://agentmods.dev/badge/skills/katekruger/campaign-preflight/preflight-campaign/github.svg)](https://agentmods.dev/skills/katekruger/campaign-preflight/preflight-campaign)
Your own site
<a href="https://agentmods.dev/skills/katekruger/campaign-preflight/preflight-campaign"><img src="https://agentmods.dev/badge/skills/katekruger/campaign-preflight/preflight-campaign/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.

agentmods 80×15 button for preflight-campaign

Your own site · 80×15
<a href="https://agentmods.dev/skills/katekruger/campaign-preflight/preflight-campaign"><img src="https://agentmods.dev/badge/skills/katekruger/campaign-preflight/preflight-campaign.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,451 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00126 $0.01451
Opus 5 $0.00063 $0.00726
Sonnet 5 $0.00025 $0.00290
Haiku 4.5 $0.00013 $0.00145

Measured 10d ago against content hash efcc53ecfa2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

preflight-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 10d 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.

skills/preflight-campaign/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Preflight a campaign

Run the bundled checker over a campaign and report what would go wrong. The checker is deterministic and read-only: it inspects, and it cannot activate, edit, or send anything.

Do this first: figure out what you were given

The user will arrive with one of four things. Identify which, then follow that path. Do not ask a long questionnaire — collect what is needed and go.

What you have Path
File paths, or an uploaded file A. Files
A lead list or copy pasted into chat B. Pasted
Only a description in conversation C. Described
Nothing yet D. Nothing

Everything ends the same way: build a campaign file and a leads CSV in a scratch directory, run the checker, and report the result in plain language.

A. Files

Confirm the paths exist, then run it. A campaign file and a leads file are required; the rest are optional and their absence is reported honestly.

"${CLAUDE_PLUGIN_ROOT}/bin/preflight" check \
  --campaign <campaign.yaml> \
  --leads <leads.csv> \
  --suppressions <suppressions.csv> \
  --evidence <evidence.json> \
  --config <preflight.yaml>

If the user uploaded a file, it is already on disk — use the path Cowork gives you. If they only have a lead list and no campaign file, treat it as path C for the campaign half: ask about the sequence and build the campaign file.

B. Pasted

Write what was pasted into a scratch directory, then run path A.

  1. Create a working directory: mktemp -d.
  2. If they pasted a lead list: write it to leads.csv. Add a header row if it is missing — read references/input-formats.md for the accepted column names, which are generous (Email/E-Mail Address/work_email all resolve).
  3. If they pasted campaign copy: build campaign.yaml around it using the template in references/input-formats.md.
  4. Fill any gap by asking, or by following path C.

Never paste contact data back into the conversation unedited. The checker redacts mailboxes by default; keep it that way.

Read the full file on GitHub · 142 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 142 lines · 126 tokens per session scan A efcc53ecfa2b

Subscribe to this mod's changes

preflight-campaign is a skill published in the GitHub repository katekruger/campaign-preflight (0 stars, last pushed 3d ago), licensed MIT. It adds 126 tokens to every session and 1,451 once invoked, about $0.0006 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 2026-08-31.