KSI Coverage Report

KSI Coverage Report is a command for Claude Code from oscal-compass-lab/compliance-trestle-skills. It costs 34 tokens per session (595 once invoked), scanned A, original, Apache-2.0.

A command that checks which of FedRAMP’s 46 Key Security Indicators have documented coverage in an OSCAL system security plan. FedRAMP is a United States government process for assessing the security of cloud services, and OSCAL is a machine-readable format for security documentation.

In plain words
What is it for?
Use it to compare an SSP JSON file with the FedRAMP 2026 rules and produce Markdown and optional JSON coverage reports.
Why use it?
It shows where the security plan already contains relevant control evidence and where documentation is missing. This helps teams assess coverage against the 2026 FedRAMP rules.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash plugins/document-transform/oscal-document-workbench/scripts/fetch-fedramp-2026-rules.sh.

Part of the oscal-document-workbench plugin — 1 skill, 8 commands shipped together

Good fit Use it to compare an SSP JSON file with the FedRAMP 2026 rules and produce Markdown and optional JSON coverage reports.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/oscal-compass-lab/compliance-trestle-skills
agentmods
npx agentmods add commands/oscal-compass-lab/compliance-trestle-skills/ksi-coverage

Made for: Claude Code.

Or install oscal-document-workbench, the plugin that ships this one along with the rest of its 1 skill, 8 commands.

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 KSI Coverage Report

README.md
[![agentmods](https://agentmods.dev/badge/commands/oscal-compass-lab/compliance-trestle-skills/ksi-coverage/github.svg)](https://agentmods.dev/commands/oscal-compass-lab/compliance-trestle-skills/ksi-coverage)
Your own site
<a href="https://agentmods.dev/commands/oscal-compass-lab/compliance-trestle-skills/ksi-coverage"><img src="https://agentmods.dev/badge/commands/oscal-compass-lab/compliance-trestle-skills/ksi-coverage/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 KSI Coverage Report

Your own site · 80×15
<a href="https://agentmods.dev/commands/oscal-compass-lab/compliance-trestle-skills/ksi-coverage"><img src="https://agentmods.dev/badge/commands/oscal-compass-lab/compliance-trestle-skills/ksi-coverage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 595 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 $0.00034 $0.00595
Opus 5 $0.00017 $0.00298
Sonnet 5 $0.00007 $0.00119
Haiku 4.5 $0.00003 $0.00060

Measured 11d ago against content hash bd090a5bb1ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

KSI Coverage Report 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 11d 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.

plugins/document-transform/oscal-document-workbench/commands/ksi-coverage.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/oscal-document-workbench:ksi-coverage

FedRAMP is moving from the legacy Rev 5 document templates to the 2026 Consolidated Rules. FedRAMP 20x certification is organized around Key Security Indicators (KSIs), not narrative SSP documents only. This command maps the SP 800-53 control IDs implemented in an OSCAL SSP onto the 46 KSIs. It reports which KSIs already have documented control coverage.

How to run

bash plugins/document-transform/oscal-document-workbench/scripts/fetch-fedramp-2026-rules.sh
bash plugins/document-transform/oscal-document-workbench/scripts/ksi-coverage-report.sh <ssp.json> --output <workspace>/reports/ksi-coverage.md --json-output <workspace>/reports/ksi-coverage.json

Arguments

  • <ssp.json> : an OSCAL system-security-plan JSON file. For example, one drafted by draft-ssp-from-extraction.sh.
  • --rules <path> : path to fedramp-consolidated-rules.json. Default is the baseline cache filled by fetch-fedramp-2026-rules.sh.
  • --output <path> : write the markdown report here. Default is stdout.
  • --json-output <path> : also write machine-readable coverage JSON.

Sources

  • FedRAMP/rules on GitHub : fedramp-consolidated-rules.json. Machine-readable source of FRD definitions, FRR requirements, KSI indicators, and CTL control requirements.
  • FedRAMP/2026-markdown on GitHub : the same rules as markdown for AI agents and text tooling.

Override the source URL with FEDRAMP_2026_RULES_URL for mirrors or air-gapped environments.

Outputs

  • ksi-coverage.md : per-KSI table. Values are covered, partial, or uncovered, with missing control IDs.
  • ksi-coverage.json : machine-readable coverage details for downstream tooling.

Exit codes

  • 0 : success
  • 2 : bad arguments, missing SSP, or missing rules file
  • 5 : download failure (fetch script)

Safety notes

  • Coverage means the SSP documents the KSI related SP 800-53 controls.
  • Coverage is documentation evidence only.
  • Coverage is not a FedRAMP 20x validation or certification result.
  • KSIs are validated by assessment and telemetry.
  • Mark uncertain mappings as needs_review in the source map before you rely on coverage numbers.
  • Do not treat structural validation as an audit opinion.
  • Do not commit sensitive customer evidence or real SSPs.

Read the full file on GitHub · 54 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. 11d ago First seen · 54 lines · 34 tokens per session scan A bd090a5bb1ea

Subscribe to this mod's changes

KSI Coverage Report is a command published in the GitHub repository oscal-compass-lab/compliance-trestle-skills (16 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 595 once invoked, about $0.0002 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.