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/congressgov-mcp-server --skill congressgov-guidegit clone --depth 1 https://github.com/cyanheads/congressgov-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/congressgov-mcp-server/congressgov-guide)<a href="https://agentmods.dev/skills/cyanheads/congressgov-mcp-server/congressgov-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/congressgov-mcp-server/congressgov-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/congressgov-mcp-server/congressgov-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/congressgov-mcp-server/congressgov-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 | $0.00048 | $0.01032 |
| Opus 5.5 | $0.00019 | $0.00413 |
| Sonnet 5.5 | $0.00010 | $0.00206 |
| Haiku 4.5 | $0.00005 | $0.00103 |
Grade A, and why
congressgov-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 2d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
Use for U.S. congressional research that follows legislation into its sponsors, committees, votes, reports, or floor debate. A topic alone needs a discovery path: the optional bill mirror searches titles and CRS summaries, not full bill text, CRS reports, or the Congressional Record.
Identifiers
Carry identifiers from returned records across tool calls:
| Entity | Provenance |
|---|---|
| Bill | Congress, bill type, and bill number from bill discovery, member portfolios, or related bills |
| Member | bioguideId from member discovery or a bill's sponsors and cosponsors |
| Committee | systemCode from committee discovery; resolve a committee name and inspect the candidates before following its legislation |
| Enacted law | laws[].number on an enacted-law row; the row's own bill number identifies the origin bill |
| Roll call | Chamber, congress, session, and roll number from vote discovery; retain the complete identity when reading detail and positions |
| Record article | Volume and issue from Record discovery, then the article's absolute position within the issue |
Gates
- Before topical discovery, check whether
congressgov_search_billsis offered. If absent, obtain a bill, member, committee, or CRS report seed; do not send a topic to browse-only tools. Committee name matching resolves committee names, not policy topics. - Before reporting no relevant bills, inspect search notices and coverage. An unbuilt mirror returns no results, and a ready mirror covers a bounded congress window and only titles and summaries. Broaden overly specific terms; report the search boundary with any negative finding.
- Before interpreting recent activity, distinguish a record's update date from its
latestAction.actionDate. The update date does not establish when legislative action occurred. - Before comparing provisions or quoting legislation, select the relevant published text version and inspect its label and any supplied date. A date may be absent; do not infer one from the bill's update date. A discovery preview or CRS summary is not the bill text; preserve the version and source URL with the evidence.
- Before interpreting a member's vote as support for a bill, inspect the roll call's question, associated measure, and result. Match the requested chamber and session; a vote associated with a bill does not by itself establish final passage.
- Before concluding a committee was resolved, inspect whether the response contains the requested detail or candidate rows. Choose a candidate by its returned name, chamber, and code; approximate matches need the same check.
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.
- 2d ago First seen · 51 lines · 48 tokens per session scan A e71d14974fbd
congressgov-guide is a skill published in the GitHub repository cyanheads/congressgov-mcp-server (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,032 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.
Other skills, from other repositories
openstates-guide
Identifier chains and gates for the openstates tools (US state legislatures via Open States). Use when tracing a state bill's fate, votes, or sponsors; finding who represents a location and their committees; finding hearings; or comparing states. Read before naming a bill, reporting who voted how, or concluding that a…
patsnap-patent-literature-search
Search Patsnap's global patent and scientific literature databases together using natural-language, semantic, keyword, and BM25-based queries with multidimensional filters, then fetch patent or literature records as Markdown.
get-started
Start with GSPC — read the live measurement board, verify a signed card, and list the signed cards relevant to one obligation. Measurement, not certification.
hold-triage
Review and process pending governance holds. Use when holds are waiting for human approval or when the user asks about blocked operations.
evidence-bundle
For ONE obligation (article-50, article-53 GPAI transparency, dora or cra) and an optional subject: the obligation record, its counsel-gate status and the already-signed measurement cards that are relevant to it, read from GET /api/evidence-bundle. The same module as the free MCP tool evidencebundlepreview.…
article50-detect
Verify a C2PA-style signed manifest for AI-generated content (EU AI Act Article 50) at POST https://councilof.ai/api/detect. Deterministically checks the Ed25519-signed metadata layer and the IPTC/schema.org digitalSourceType; returns AIMARKED / NOTAIMARKED / UNVERIFIABLE with a signed verdict receipt (in-toto/DSSE…