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 hartmut-ux/ai-marketing-team --skill government-affairsgit clone --depth 1 https://github.com/hartmut-ux/ai-marketing-teamWrote 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/hartmut-ux/ai-marketing-team/government-affairs)<a href="https://agentmods.dev/skills/hartmut-ux/ai-marketing-team/government-affairs"><img src="https://agentmods.dev/badge/skills/hartmut-ux/ai-marketing-team/government-affairs/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/hartmut-ux/ai-marketing-team/government-affairs"><img src="https://agentmods.dev/badge/skills/hartmut-ux/ai-marketing-team/government-affairs.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 | $0.00067 | $0.00243 |
| Opus 5 | $0.00034 | $0.00121 |
| Sonnet 5 | $0.00013 | $0.00049 |
| Haiku 4.5 | $0.00007 | $0.00024 |
Grade A, and why
government-affairs 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 12d 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.
What it actually says
Government Affairs — Claude Code wrapper
This is the Claude Code wrapper for government-affairs. The full skill definition lives in shared/SKILL-CORE.md in the same skill folder.
When to use
Use when the user asks for:
government-affairs- "run government-affairs"
- Any trigger described in the core skill
How to invoke
In Claude Code:
government-affairs
Instructions
- Read
shared/SKILL-CORE.mdfor the platform-agnostic workflow, rules, and examples. - Execute the workflow using Claude Code tools.
- Load any referenced files from
shared/or subdirectories relative to this skill folder.
References
shared/SKILL-CORE.md— full skill definition
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.
- 12d ago First seen · 34 lines · 67 tokens per session scan A b1a138ae383d
government-affairs is a skill published in the GitHub repository hartmut-ux/ai-marketing-team (11 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 243 once invoked, about $0.0003 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 skills, from other repositories
kelly-legal-contracts
A review desk for business contracts such as non-disclosure agreements, service agreements, data-processing agreements, and statements of work. It compares clauses with a company's approved playbook and records review decisions.
kelly-disclosure-tracker
Cross-Entity Disclosure Tracker App-in-Skill — a Busabase review workspace that helps a compliance/IR team assemble and track a standardized disclosure package per financing vehicle (fund/SPV), across a generic onshore origination entity, an offshore fund-manager entity, and a listing/exchange venue. Use when the user…
kelly-legal-casebase-ingest
A review workspace for turning court judgments and arbitration awards into anonymized, structured internal case records. Court judgments and arbitral awards are written decisions that explain disputes and their outcomes.
kelly-legal-firm-radar
A dashboard for analyzing anonymized law-firm case information, lawyer capabilities and business performance. It prepares management insights and reports for review before export.
kelly-legal-matter-strategy
A reviewer-controlled workspace for planning legal cases from facts and internal precedents. It produces issue trees, evidence lists, risk assessments, negotiation options, and outlines for pleadings or legal memos.
kelly-legal-precedent-desk
A reviewer-controlled research desk for finding similar cases in an internal legal casebase. It packages comparable facts, local court tendencies, important evidence, decisions, and citations into a research memo.