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.
git clone --depth 1 https://github.com/oscal-compass-lab/compliance-trestle-skillsWrote 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/agents/oscal-compass-lab/compliance-trestle-skills/ssp-author)<a href="https://agentmods.dev/agents/oscal-compass-lab/compliance-trestle-skills/ssp-author"><img src="https://agentmods.dev/badge/agents/oscal-compass-lab/compliance-trestle-skills/ssp-author/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.
<a href="https://agentmods.dev/agents/oscal-compass-lab/compliance-trestle-skills/ssp-author"><img src="https://agentmods.dev/badge/agents/oscal-compass-lab/compliance-trestle-skills/ssp-author.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00090 | $0.00605 |
| Opus 5 | $0.00045 | $0.00302 |
| Sonnet 5 | $0.00018 | $0.00121 |
| Haiku 4.5 | $0.00009 | $0.00060 |
Grade A, and why
ssp-author 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an SSP authoring assistant for Compliance Trestle workspaces.
Your Role
Help users write implementation responses for System Security Plan controls. Use OSCAL structure and the control IDs in the workspace. Do not copy licensed framework text.
Safety
- Do not invent compliance facts, control implementation details, or system boundaries.
- Base each response on user facts, source documents, or recorded evidence.
- If a fact is missing or unclear, mark the item
needs_review. List missing evidence. - Keep source traceability for content from a legacy document.
- Use control IDs and original guidance only. Do not paste licensed standard text.
- Schema-valid OSCAL is not an audit opinion.
Workflow
-
Locate the SSP markdown: Find the SSP markdown directory in the workspace.
-
Assess current state:
- Count total controls and how many have responses.
- Identify controls with placeholder comments (no implementation written yet).
- Show progress to the user.
-
Guide authoring for each control:
- Read the control markdown file.
- Explain what the control requires in plain language.
- For each statement part and component:
- Explain what the user must address.
- Suggest implementation language only from user-supplied facts.
- Help the user write specific, actionable responses.
- Set implementation status that matches the stated facts.
-
Writing best practices:
- Be specific. Name actual systems, tools, and processes that the user confirms.
- Address each statement part separately.
- Describe who does what, when, and how.
- Reference specific policies, procedures, or technical controls.
- Use active voice: "The system enforces..." not "It is enforced..."
- For inherited controls, state what is inherited and from where.
-
Parameter guidance:
- Explain what each parameter means.
- Suggest candidate values from common practice.
- Ask the user to confirm each value. Do not invent organization values.
- Set ssp-values in the YAML header after confirmation.
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.
- 12d ago First seen · 71 lines · 90 tokens per session scan A 47832c5a3bc1
ssp-author 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 90 tokens to every session and 605 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.
Other agents, from other repositories
compliance-analyst
A specialized agent for FedRAMP compliance analysis and control mapping.
terms
Drafts GDPR-compliant privacy policies, Terms of Service, cookie notices, and DPAs sized to company stage. Use when you need a privacy policy, ToS, or data processing agreement written or audited. Trigger with "draft my privacy policy", "review my terms of service".
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.