sam-gov

sam-gov is a skill for Claude Code from cliwant/mcp-sam-gov. It costs 295 tokens per session (9,894 once invoked), scanned A, original, MIT.

A skill for querying and analyzing US federal contracting, government spending, regulations, company vetting, and market data through SAM.gov and related sources. SAM.gov is the US government portal for contracting opportunities and registrations.

In plain words
What is it for?
Use it to find opportunities, read RFP and statement-of-work documents, build FAR or DFARS compliance checks, vet companies, estimate markets, price bids, and review economic data.
Why use it?
Federal contracting research often requires checking many separate records, documents, rules, and financial or compliance details. This brings those investigations into one workflow.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: positional $N argument; mentions Claude Code.

Part of the sam-gov plugin — 1 skill, 2 MCP servers shipped together

Good fit Use it to find opportunities, read RFP and statement-of-work documents, build FAR or DFARS compliance checks, vet companies, estimate markets, price bids, and review economic data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cliwant/mcp-sam-gov/sam-gov
Install

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.

Any agent
npx skills add cliwant/mcp-sam-gov --skill sam-gov
Clone the repo
git clone --depth 1 https://github.com/cliwant/mcp-sam-gov

Made for: Claude Code.

Or install sam-gov, the plugin that ships this one along with the rest of its 1 skill, 2 MCP servers.

Wrote 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.

agentmods badge for sam-gov

README.md
[![agentmods](https://agentmods.dev/badge/skills/cliwant/mcp-sam-gov/sam-gov/github.svg)](https://agentmods.dev/skills/cliwant/mcp-sam-gov/sam-gov)
Your own site
<a href="https://agentmods.dev/skills/cliwant/mcp-sam-gov/sam-gov"><img src="https://agentmods.dev/badge/skills/cliwant/mcp-sam-gov/sam-gov/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.

agentmods 80×15 button for sam-gov

Your own site · 80×15
<a href="https://agentmods.dev/skills/cliwant/mcp-sam-gov/sam-gov"><img src="https://agentmods.dev/badge/skills/cliwant/mcp-sam-gov/sam-gov.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 295 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,894 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00295 $0.09894
Opus 5 $0.00148 $0.04947
Sonnet 5 $0.00059 $0.01979
Haiku 4.5 $0.00030 $0.00989

Measured 10d ago against content hash a2267d76fc6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sam-gov 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.

skills/sam-gov/SKILL.md · 376 lines

How it starts

The opening of the file, as written. The whole thing — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SAM.gov federal-data skill — 150 tools across 52 sources

This skill teaches Claude how to use the sam-gov MCP server (150 tools wrapped from @cliwant/mcp-sam-gov) to answer the full surface of US federal contracting / spending / regulation / vetting / market questions end-to-end — from discovering (and shaping) an opportunity, to reading the actual RFP/SOW documents, running a FAR/DFARS compliance matrix, vetting a firm (sanctions, exclusions, audits, bank health, EPA), sizing a market (establishments + wages + regional GDP), pricing the bid against statutory wage floors, and pulling macro context for escalation.

Setup: the sam-gov MCP server must be reachable. /plugin install cliwant/mcp-sam-gov registers it automatically; otherwise see the repo README. Host prefixing: Claude Code exposes tools as mcp__sam-gov__<tool>; bare MCP hosts use just <tool>. Use whichever your host gives you.

Tool inventory — 150 tools, keyless-first

Keyless-first: 48 of 52 sources need no key. Only 4 sources require a free key (marked 🔑 below): Census CBP (census_business_patterns), FRED (fred_search_series, fred_series_observations), BEA (bea_regional_data), and DOL's data endpoint (dol_get_dataset; DOL's catalog is keyless). Those 4 tools throw an honest config error without a key. A handful of others take an optional free key for higher limits (see the Keys section). The server is the only source of truth — never invent notice IDs, officer names, award amounts, NAICS codes, or regulation citations.

Opportunities & solicitations — SAM.gov + Grants.gov (10)

  • sam_search_opportunities — search active SAM.gov contracting opportunities (filters: query, ncode/NAICS, organizationName, state, setAside, limit).
  • sam_search_shapingpre-solicitation radar: Sources Sought / Presol / Special Notices before the RFP exists (keyless rows null naics/setAside/place — get those via sam_get_opportunity).
  • sam_get_opportunity — full detail for ONE notice by 32-char hex noticeId (POCs, deadline, attachments[], body). Call BEFORE bid/no-bid or compliance work.
  • sam_fetch_description — full SOW/RFP body as plain text (when detail gave a description URL not inline body).
  • sam_fetch_attachment_textREAD the attachment (RFP/SOW/Q&A/wage PDF+DOCX+HTML) by its attachments[].url. A scanned/image-only or unreadable doc returns text:null + disclosed reason (honest, not a bug).
  • sam_attachment_url — build the public download URL for an attachment resourceId (303 → signed S3).
  • sam_lookup_organization — federal-organization id → canonical fullParentPathName.
  • sam_lookup_notice_fieldsbatch-fill nulled naics/setAside/PoP/deadline for 1–100 noticeIds from the opt-in GSA daily CSV. OFF by default (returns enabled:false until SAM_GOV_ENABLE_CSV=1); snapshot can lag ~24h.
  • grants_search — Grants.gov federal grant opportunities (financial assistance, distinct from contracts).
  • grants_get_opportunity — full grant detail (description, dates, award ceiling, applicant types, CFDA).

Read the full file on GitHub · 376 lines

Changes

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.

  1. 10d ago First seen · 376 lines · 295 tokens per session scan A a2267d76fc6c

Subscribe to this mod's changes

sam-gov is a skill published in the GitHub repository cliwant/mcp-sam-gov (6 stars, last pushed 2d ago), licensed MIT. It adds 295 tokens to every session and 9,894 once invoked, about $0.0015 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.

Related

Other skills, from other repositories

security-compliance

Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.

sangrokjung/claude-forge · 56 tokens

agb-begriff-vorformuliert-305

Für AGB Begriff Vorformuliert 305: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-begriff-vorformuliert-305.

Klotzkette/claude-fuer-deutsches-recht · 68 tokens

aenderungsvorbehalt-308

Für Änderungsvorbehalt 308: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.

Klotzkette/claude-fuer-deutsches-recht · 41 tokens

agb-pruefung-kaltstart

Für AGB Prüfung Kaltstart: routet Rolle, Frist, Unterlagen und Fachschritt; Ergebnis: Tatbestands- oder Anspruchsmatrix.

Klotzkette/claude-fuer-deutsches-recht · 41 tokens

agb-rechtswahl-schweizer-recht-rom-i

Für AGB Rechtswahl Schweizer Recht Rom I: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-rechtswahl-schweizer-recht-rom-i.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

aufrechnung-zurueckbehaltung-309

Für Aufrechnung Zurückbehaltung 309: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.

Klotzkette/claude-fuer-deutsches-recht · 43 tokens