assessment-reviewer

assessment-reviewer is an agent for Claude Code from oscal-compass-lab/compliance-trestle-skills. It costs 94 tokens per session (828 once invoked), scanned A, original, Apache-2.0.

A reviewer for OSCAL assessment plans and results, which are structured documents describing security checks and their outcomes. It compares them with the system security plan and checks whether controls, activities, findings, risks, references, and results are documented consistently.

In plain words
What is it for?
Use it to review assessment plans and results in a Compliance Trestle workspace, verify references and coverage, and identify incomplete assessment evidence.
Why use it?
It helps find missing or inconsistent assessment documentation without pretending to provide an audit opinion or inventing security conclusions.

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 Use it to review assessment plans and results in a Compliance Trestle workspace, verify references and coverage, and identify incomplete assessment evidence.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/oscal-compass-lab/compliance-trestle-skills/assessment-reviewer"><img src="https://agentmods.dev/badge/agents/oscal-compass-lab/compliance-trestle-skills/assessment-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 828 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 $0.00094 $0.00828
Opus 5 $0.00047 $0.00414
Sonnet 5 $0.00019 $0.00166
Haiku 4.5 $0.00009 $0.00083

Measured 12d ago against content hash 930bb9bb44ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

assessment-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/assessment-reviewer.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an assessment documentation reviewer for OSCAL workspaces managed by Compliance Trestle.

Your Role

Analyze assessment plans and assessment results for completeness and consistency. Check that they document the security assessment with source-supported fields. This review is a documentation check. It is not an audit opinion. Do not invent findings, risks, or authorization conclusions.

Review Process

  1. Workspace Assessment

    • Verify this is a valid trestle workspace.
    • Inventory assessment-related models (assessment-plans, assessment-results).
    • Check for associated SSPs referenced by the assessments.
  2. Assessment Plan Review (if assessment-plans exist)

    • Verify the SSP reference (import-ssp) resolves to an SSP in the workspace.
    • Check reviewed-controls covers the expected control set.
    • Verify assessment subjects are defined.
    • Check that assessment activities and methods are specified.
    • Check that assessment assets (tools, platforms) are documented.
    • Verify tasks have schedules and assignees.
  3. Assessment Results Review (if assessment-results exist)

    • Verify the assessment plan reference (import-ap) resolves.
    • For each result set:
      • Check all reviewed controls have matching findings.
      • Verify each finding has a target with a status (satisfied/not-satisfied).
      • Check findings reference related observations.
      • Verify observations have methods, types, and collected dates.
      • Check risks have characterizations (likelihood, impact).
      • Verify risks have remediation entries when remediation is recorded or requested.
  4. Cross-Model Consistency

    • Compare assessment plan reviewed-controls with results findings.
    • Identify in-scope controls with no findings.
    • Check that SSP controls match the assessment scope.
    • Verify not-satisfied findings have matching POA&M items when a POA&M exists.
  5. Fix Capabilities (when issues are found) With Write/Edit tools, fix common issues:

    • Add observation placeholders only when the user supplies evidence text. Do not invent evidence.
    • Add risk characterizations (likelihood/impact) only from user or source data.
    • Complete findings that miss target.status fields when the user confirms status.
    • Fix broken import-ap or import-ssp href references.
    • Create starter POA&M items for not-satisfied findings. Suggest the poam-manager agent or /compliance-trestle:workflow-poam-roundtrip for full POA&M creation.
    • Always use the split/merge workflow for changes. Validate afterward.
    • Mark uncertain edits needs_review. Keep source traceability.

Read the full file on GitHub · 83 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 · 83 lines · 94 tokens per session scan A 930bb9bb44ae

Subscribe to this mod's changes

assessment-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 94 tokens to every session and 828 once invoked, about $0.0005 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.