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 sh-patterson/fec-mcp-server --skill fec-campaign-finance-researchgit clone --depth 1 https://github.com/sh-patterson/fec-mcp-serverWrote 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/sh-patterson/fec-mcp-server/fec-campaign-finance-research)<a href="https://agentmods.dev/skills/sh-patterson/fec-mcp-server/fec-campaign-finance-research"><img src="https://agentmods.dev/badge/skills/sh-patterson/fec-mcp-server/fec-campaign-finance-research/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/sh-patterson/fec-mcp-server/fec-campaign-finance-research"><img src="https://agentmods.dev/badge/skills/sh-patterson/fec-mcp-server/fec-campaign-finance-research.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 | $0.00051 | $0.00615 |
| Opus 5 | $0.00026 | $0.00308 |
| Sonnet 5 | $0.00010 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
fec-campaign-finance-research 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.
How it starts
The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FEC campaign finance research
Use the FEC MCP tools for federal records only.
- Run
search_candidateswhen you need a candidate or principal committee ID. - State that no result was found in the searched federal records. Do not infer that a person or race is non-federal.
- Use
get_committee_financesfor a committee-level summary. - Use
get_receipts,get_disbursements, orget_independent_expendituresfor transaction detail. - Use
search_donorsorsearch_spendingonly for cross-committee searches. - Use
get_committee_flagsfor filing records. Do not describe a flag as a violation.
When you compare a summary with transactions, pass the same value for cycle and two_year_transaction_period. Use narrow filters and a small limit first. State the filters, cycle, result count, and returned-row count in the answer.
OpenFEC refreshes nightly. Cached results can remain stale for up to one hour. A returned page is not a complete result set. Treat large result counts as approximate.
Continue a search
The following tools support continuation: search_candidates, get_receipts, get_disbursements, get_independent_expenditures, search_donors, and search_spending.
When a result includes Continuation: {"continuation":"fecp1..."}, paste that JSON value into the next call as the continuation field. Keep every other filter unchanged. Continue until the footer says Continuation: none. A keyset route can return an empty terminal page. The server rejects a token when filters change or when a token is used with a different tool.
Treat continuation tokens as unsigned, stateless, and opaque. Do not decode, edit, or construct one. Candidate tokens advance OpenFEC page numbers. Transaction tokens advance OpenFEC keyset cursors. Candidate page membership is not guaranteed to stay stable across OpenFEC refreshes.
Read the footer count status as exact, approximate, or unspecified. Report exact counts as exact records. Report approximate counts as reported records. Report unspecified counts without claiming a total. Preserve source record IDs and OpenFEC-returned URLs when you cite a record.
What ships with it
1 file 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.
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 · 51 tokens per session scan A d34fa05cb1a5
fec-campaign-finance-research is a skill published in the GitHub repository sh-patterson/fec-mcp-server (4 stars, last pushed 18d ago), licensed MIT. It adds 51 tokens to every session and 615 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 2026-08-31.
Other skills, from other repositories
openclaw-api-monitor
API monitoring and cost tracking MCP server with 5 tools for AI providers. Use when: (1) 'is OpenAI API down' or 'check Anthropic status', (2) 'how many tokens have I used today' or 'API usage stats', (3) 'alert me when I spend $50' or 'budget limit notification', (4) 'how much am I spending on each provider' or 'cost…
openclaw-crypto-payments
Skill "openclaw-crypto-payments" from yedanyagamiai-cmd/openclaw-mcp-servers, covering openclaw crypto payments v2.0, what's new in v2.0, quick start, detection triggers and named protocols.
openclaw-revenue-tracker
Revenue tracking MCP server with 4 tools for Stripe, PayPal, Gumroad, and crypto sources. Use when: (1) 'how much did I make today' or 'total revenue this month', (2) 'new order came in' or 'log this sale', (3) 'daily revenue report' or 'breakdown by product', (4) 'alert me when I hit $1000' or 'milestone…
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
add-tool
Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.