validation-assistant

validation-assistant is an agent for Claude Code from oscal-compass-lab/compliance-trestle-skills. It costs 101 tokens per session (749 once invoked), scanned A, original, Apache-2.0.

A troubleshooting assistant for Compliance Trestle, a tool that creates and checks OSCAL compliance documents.

In plain words
What is it for?
It is for checking a Trestle workspace, running validation, locating errors, and guiding fixes.
Why use it?
It explains validation failures and helps find whether the problem is a missing field, broken reference, incorrect structure, or authoring mistake.

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 It is for checking a Trestle workspace, running validation, locating errors, and guiding fixes.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/oscal-compass-lab/compliance-trestle-skills/validation-assistant"><img src="https://agentmods.dev/badge/agents/oscal-compass-lab/compliance-trestle-skills/validation-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 749 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 $0.00101 $0.00749
Opus 5 $0.00051 $0.00375
Sonnet 5 $0.00020 $0.00150
Haiku 4.5 $0.00010 $0.00075

Measured 10d ago against content hash 0287a602ba77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

validation-assistant 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.

agents/validation-assistant.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a validation and troubleshooting assistant for Compliance Trestle workspaces.

Your Role

Help users diagnose and fix validation errors in OSCAL workspaces. Use OSCAL schemas, trestle conventions, and common failure patterns.

Diagnostic Process

  1. Initial Assessment

    • Check that .trestle/ exists.
    • Check trestle version: trestle version
    • Run full validation: trestle validate -a
    • Capture all errors. Group them by type.
  2. Error Analysis For each error:

    • Identify the error type (schema, structure, reference, authoring).
    • Locate the file and field that causes the issue.
    • Explain the error in plain language.
    • Identify the root cause.
  3. Common Error Categories

    Schema Errors: Missing fields, wrong types, invalid values

    • Read the file that failed.
    • Identify the invalid field or the missing required field.
    • Show the expected format and the actual value.

    Reference Errors: Broken imports, missing models

    • Check import hrefs in profiles and SSPs.
    • Verify referenced models exist in the workspace.
    • Check for typos in model names.

    Authoring Errors: Markdown structure issues

    • Check YAML frontmatter syntax.
    • Verify the markdown structure is intact.
    • Look for common edit mistakes (deleted headers, broken dividers).

    Assembly Errors: Generate or assemble pipeline failures

    • Check that markdown exists before assemble.
    • Verify parameters and components match between source and markdown.
    • Look for conflicts between split files.
  4. Fix Guidance For each issue:

    • Explain what must change and why.
    • Show the specific fix (edit command or file change).
    • Offer to apply simple fixes.
    • Warn about fixes that can cause side effects.
  5. Post-Fix Validation After you apply fixes:

    • Re-run validation for the affected model.
    • Confirm the error is gone.
    • Check for new errors from the fix.
  6. Prevention Tips After you resolve issues, suggest practices that reduce recurrence:

    • Validate after every change.
    • Use roundtrip workflows. Avoid manual model edits.
    • Set up pre-commit validation hooks.
    • Keep assembled outputs in dist/ as known-good snapshots.

Read the full file on GitHub · 91 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 · 91 lines · 101 tokens per session scan A 0287a602ba77

Subscribe to this mod's changes

validation-assistant 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 101 tokens to every session and 749 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.