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 agentmods add commands/hackidle/fedramp-docs-mcp/evidence-examplesgit clone --depth 1 https://github.com/hackIDLE/fedramp-docs-mcpWrote 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/commands/hackidle/fedramp-docs-mcp/evidence-examples)<a href="https://agentmods.dev/commands/hackidle/fedramp-docs-mcp/evidence-examples"><img src="https://agentmods.dev/badge/commands/hackidle/fedramp-docs-mcp/evidence-examples.svg" alt="Measured on agentmods" 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 | $0.00008 | $0.00391 |
| Opus 5 | $0.00004 | $0.00196 |
| Sonnet 5 | $0.00002 | $0.00078 |
| Haiku 4.5 | $0.00001 | $0.00039 |
Grade A, and why
evidence-examples scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Evidence Examples
Get evidence examples for FedRAMP compliance automation.
Filter by theme or KSI ID: "$ARGUMENTS" (optional)
Use the fedramp-docs MCP server's get_evidence_examples tool to collect all evidence examples needed for compliance. Show examples of required evidence organized by KSI theme.
What's Included
The evidence examples database contains 830+ automation sources from 50+ providers including:
- Cloud Platforms: AWS, Azure, GCP, Oracle Cloud
- Identity & Access: Okta (with WebAuthn/FIDO2), Duo, Entra ID, CrowdStrike Identity
- Security Tools: Splunk, Sentinel, Palo Alto, CrowdStrike, Veracode
- Collaboration: Google Workspace, Microsoft 365, Webex, Zoom, Box
- DevOps: GitHub, GitLab, Terraform, Docker, Kubernetes
Each source includes:
- Provider and service name
- API endpoints or CLI commands
- Specific evidence collection guidance
- Official documentation links
- Compliance tips and gotchas
Example Use Cases
Phishing-Resistant MFA (KSI-IAM-01):
- Okta WebAuthn factor verification
- Duo passkey enrollment checks
- Entra ID authentication strength policies
Network Security (KSI-CNA-01):
- AWS Security Group rules
- Kubernetes NetworkPolicy configs
- GCP VPC firewall rules
Vulnerability Management (KSI-VUL-*):
- Container image scanning (Snyk, Aqua)
- Dependency scanning (Dependabot)
- Infrastructure scanning (Prowler, ScoutSuite)
Disclaimer
These are community-suggested automation approaches, not official FedRAMP guidance. Always verify with your 3PAO and FedRAMP PMO.
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.
- 3d ago First seen · 50 lines · 8 tokens per session scan A e36f9e7eb73f
evidence-examples is a command published in the GitHub repository hackIDLE/fedramp-docs-mcp (18 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 391 once invoked, about $0.0000 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 commands, from other repositories
Ingest Legacy SSP
Run the end-to-end legacy SSP import process: extract source material, create source traceability, bootstrap a Trestle workspace, map content, validate OSCAL, and report unmapped items.
Fetch OSCAL Baseline
Download the NIST SP 800-53 Rev 5 catalog and a FedRAMP Rev 5 baseline profile, then import both into a Compliance Trestle workspace for real-baseline SSP drafting.
KSI Coverage Report
Compare an OSCAL SSP to the FedRAMP 20x Key Security Indicators from the 2026 Consolidated Rules and report documentation coverage.
Validate OSCAL Package
Validate an OSCAL file or Trestle package with available validators and write a validation summary.
concept
Teach one GRC engineering concept in plain language.
scenario
Generate a fictional scenario and grade the learner's response.