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.
/plugin marketplace add katekruger/campaign-preflight/plugin install campaign-preflightWrote 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/katekruger/campaign-preflight/preflight-demo)<a href="https://agentmods.dev/skills/katekruger/campaign-preflight/preflight-demo"><img src="https://agentmods.dev/badge/skills/katekruger/campaign-preflight/preflight-demo/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/katekruger/campaign-preflight/preflight-demo"><img src="https://agentmods.dev/badge/skills/katekruger/campaign-preflight/preflight-demo.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 | $0.00118 | $0.00683 |
| Opus 5 | $0.00059 | $0.00342 |
| Sonnet 5 | $0.00024 | $0.00137 |
| Haiku 4.5 | $0.00012 | $0.00068 |
Grade A, and why
preflight-demo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Show the demo
Run the bundled demo and walk the user through what it caught.
"${CLAUDE_PLUGIN_ROOT}/bin/preflight" demo
Takes about a fiftieth of a second. No credentials, no network, no setup.
What the demo campaign contains
Twenty synthetic contacts and a three-step sequence, broken on purpose so one run demonstrates every kind of result. Highlights worth pointing out:
- Stop-on-reply is off on a three-step sequence — repliers keep getting follow-ups.
- A contact who unsubscribed is still on the list, and another is at a domain that opted out entirely.
- Prompt-injection text sitting in a personalization field, scraped in from a page the target controls, queued to send under the user's domain.
- An unrendered
{{first_name}}that never merged. - A greeting addressed to the wrong person — the signature of a mis-joined enrichment table.
- A
TODOand a broken link still in the copy. - One sender with no health score and no daily limit, which is why sender
capacity comes back
UNKNOWN.
The point to land
That last one is the interesting one, and it is worth drawing attention to.
Most tools would add up the two senders that do report a limit and print a
capacity number. This one reports UNKNOWN and names the mailbox it could not
assess — and drops confidence from HIGH to MEDIUM because of it.
Say it roughly this way:
Notice the last section. It's not claiming the senders are fine and it's not claiming they're broken — it's saying it couldn't tell, and which one it couldn't tell about. A checker that can't distinguish "I looked and it's fine" from "I couldn't look" will eventually turn a permissions error into a green light.
Other formats, if asked
"${CLAUDE_PLUGIN_ROOT}/bin/preflight" demo --format markdown # to paste into a doc
"${CLAUDE_PLUGIN_ROOT}/bin/preflight" demo --verbose # explanations + score arithmetic
Then offer the obvious next step
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.
- 10d ago First seen · 68 lines · 118 tokens per session scan A 3aeb1f39f2e6
preflight-demo is a skill published in the GitHub repository katekruger/campaign-preflight (0 stars, last pushed 3d ago), licensed MIT. It adds 118 tokens to every session and 683 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.
Other skills, from other repositories
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
ln-62-repository-publisher
Commits, pushes, and remotely verifies authorized repository changes. Not for releases, package publication, or announcements.
remove
Remove a deployed framework or addon from the current workspace.
maggy
Maggy is a local AI engineering command center. AI-prioritized inbox across issue trackers (GitHub Issues/Asana), one-click TDD execute with iCPG context enrichment, daily competitor intelligence briefing.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.