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 cyanheads/openfec-mcp-server --skill openfec-guidegit clone --depth 1 https://github.com/cyanheads/openfec-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/cyanheads/openfec-mcp-server/openfec-guide)<a href="https://agentmods.dev/skills/cyanheads/openfec-mcp-server/openfec-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/openfec-mcp-server/openfec-guide/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/cyanheads/openfec-mcp-server/openfec-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/openfec-mcp-server/openfec-guide.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 | $0.00053 | $0.01091 |
| Opus 5.5 | $0.00021 | $0.00436 |
| Sonnet 5.5 | $0.00011 | $0.00218 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
openfec-guide 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 9d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
Use OpenFEC for federal campaign-finance research and FEC legal records. Near-real-time e-filing data is outside this server's scope; do not use an empty result to rule out a newly filed report.
Identifiers
- Resolve a candidate's name with
openfec_search_candidates. Carry the returned candidate ID and race geography into the investigation. - Resolve the cycle's principal campaign committee from that candidate's
openfec_lookup_electionssearch row:candidate_pcc_ididentifies the committee andcandidate_pcc_namenames it. Page the race until the candidate is found. - Use
openfec_search_committeesto resolve a PAC by name or discover a candidate's related committees. Keep each returned committee ID attached to its own records. - For legal detail, take
noanddocument_typefromopenfec_search_legal.openfec_get_legal_documentaccepts the plural form of that document type; do not substitute a committee ID or infer a case number from the search text.
Gates
- Establish historical affiliation before attributing money. A committee's designation is current even when a committee search is cycle-filtered. Do not use a current principal designation as proof of the principal committee for a past race; use the race's candidate row.
- Match reporting scope before comparing amounts. Carry the requested cycle through financial calls and inspect
search_criteriaand coverage dates. Race totals and aggregated independent expenditures can cover a full election period; choose the period the question requires before comparing them with cycle-scoped transactions. Label unequal coverage rather than presenting it as a like-for-like comparison. - Use reported totals for financial summaries. Start with candidate or committee totals rather than treating a page of transactions as total receipts or spending. A totals lookup with no record can mean no filing for the selected cycle, not an unknown committee.
- Preserve committee boundaries. Candidate totals do not include every leadership PAC or joint fundraising committee associated with that candidate. Retrieve related committees' own totals and report them separately.
- Check the selected mode before narrowing a question. Aggregate modes do not support every itemized filter. If the question depends on a donor, payee, date, or amount filter that only itemized mode supports, use itemized records rather than dropping the filter to obtain an aggregate.
- Establish coverage before claiming completeness or absence. Follow the response's continuation mechanism. A short page can be bounded by the server; an empty page can be an exhausted position in a nonempty result set. Restart an itemized search when changing its filters instead of reusing its cursor. Treat counts marked approximate as estimates.
- Read the legal record before characterizing its outcome. Search results summarize documents, dispositions, and votes. Fetch detail and retrieve any relevant withheld arrays before reporting the record complete. Legal search is full-text rather than entity-linked: no name match does not establish that a committee has no cases.
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.
- 9d ago First seen · 52 lines · 53 tokens per session scan A 42555fedda4e
openfec-guide is a skill published in the GitHub repository cyanheads/openfec-mcp-server (2 stars, last pushed 10d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,091 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-28.
openfec-guide compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| openfec-guidecyanheads/openfec-mcp-server | Skill | 2 | 10d ago | Apache-2.0 | A | 53 | Claude Code |
| fec-campaign-finance-researchsh-patterson/fec-mcp-server | Skill | 4 | 1mo ago | MIT | A | 51 | Codex |
| blazemeter-usage-billingBlazemeter/bzm-mcp | Skill | 26 | 11d ago | Apache-2.0 | A | 67 | Claude Code, Codex |
| award-travelAwardTravelFinder/mcp | Skill | 12 | 6d ago | MIT | A | 164 | Claude Code |
| find-my-bookings-and-balancesAwardTravelFinder/mcp | Skill | 12 | 6d ago | MIT | A | 97 | Claude Code |
| cancel-or-change-awardAwardTravelFinder/mcp | Skill | 12 | 6d ago | MIT | A | 69 | Claude Code |
| maximize-transfer-bonusAwardTravelFinder/mcp | Skill | 12 | 6d ago | MIT | A | 71 | Claude Code |