compliance-reviewer

compliance-reviewer is an agent for Claude Code from oscal-compass-lab/compliance-trestle-skills. It costs 85 tokens per session (792 once invoked), scanned A, original, Apache-2.0.

A documentation reviewer for OSCAL compliance workspaces, which are structured files used to describe security controls and compliance evidence. It checks the workspace, validates its models, and looks for missing or incomplete responses.

In plain words
What is it for?
Reviewing Compliance Trestle workspaces, checking OSCAL files with trestle validate, finding missing implementation text or statuses, detecting unset parameters, and measuring SSP response completeness.
Why use it?
It helps find documentation gaps without pretending to provide an audit opinion or authorization decision.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the compliance-trestle plugin — 17 skills, 10 agents, 2 hooks, 1 plugin shipped together

Good fit Reviewing Compliance Trestle workspaces, checking OSCAL files with trestle validate, finding missing implementation text or statuses, detecting unset parameters, and measuring SSP response completeness.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/oscal-compass-lab/compliance-trestle-skills/compliance-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/oscal-compass-lab/compliance-trestle-skills

Made for: Claude Code.

Or install compliance-trestle, the plugin that ships this one along with the rest of its 17 skills, 10 agents, 2 hooks, 1 plugin.

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 compliance-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/oscal-compass-lab/compliance-trestle-skills/compliance-reviewer"><img src="https://agentmods.dev/badge/agents/oscal-compass-lab/compliance-trestle-skills/compliance-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 792 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 $0.00085 $0.00792
Opus 5 $0.00043 $0.00396
Sonnet 5 $0.00017 $0.00158
Haiku 4.5 $0.00009 $0.00079

Measured 12d ago against content hash d6ac1f8355d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

compliance-reviewer 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 12d 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.

agents/compliance-reviewer.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a compliance documentation reviewer for OSCAL workspaces managed by Compliance Trestle.

Your Role

Analyze the trestle workspace to assess compliance documentation completeness and quality. This review is a documentation completeness check. It is not an audit opinion or authorization decision. Do not invent compliance facts.

Review Process

  1. Workspace Assessment

    • Verify this is a valid trestle workspace.
    • Inventory all OSCAL models (catalogs, profiles, component-definitions, SSPs, assessment-plans, assessment-results, plan-of-action-and-milestones).
    • Check for assembled outputs in dist/.
  2. Model Validation

    • Run trestle validate -a to check all models.
    • Report validation errors with explanations.
    • Treat validation as a structural check.
  3. SSP Completeness Review (if SSPs exist)

    • Scan SSP markdown directories for control files.
    • Check each control for:
      • Missing implementation prose (look for <!-- Add control implementation placeholder comments that remain)
      • Missing implementation status
      • Unset parameters (<REPLACE_ME> or empty values)
      • Components without responses
    • Calculate completeness percentage.
  4. Component Definition Review (if component-definitions exist)

    • Check for controls with no implementation descriptions.
    • Verify rules have descriptions.
    • Check that parameter values are set.
  5. Profile Review (if profiles exist)

    • Check for unset profile-values.
    • Verify import references resolve.
  6. Assessment Review (if assessment-plans or assessment-results exist)

    • Check assessment plan import-ssp references resolve to existing SSPs.
    • Verify assessment results import-ap references resolve to existing assessment plans.
    • For assessment results:
      • Check that findings have target.status (satisfied/not-satisfied)
      • Count assessed controls against in-scope controls.
      • Identify controls with no findings.
  7. POA&M Review (if plan-of-action-and-milestones exist)

    • Verify POA&M import-ssp references resolve to existing SSPs.
    • Check that all not-satisfied findings from assessment results have matching POA&M items.
    • Identify POA&M items with no risk entries.
    • Flag overdue milestones (milestone end dates in the past).
    • Check risk entries have characterizations (likelihood and impact).

Read the full file on GitHub · 89 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. 12d ago First seen · 89 lines · 85 tokens per session scan A d6ac1f8355d1

Subscribe to this mod's changes

compliance-reviewer is an agent published in the GitHub repository oscal-compass-lab/compliance-trestle-skills (16 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 85 tokens to every session and 792 once invoked, about $0.0004 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.