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/poam-manager)<a href="https://agentmods.dev/agents/oscal-compass-lab/compliance-trestle-skills/poam-manager"><img src="https://agentmods.dev/badge/agents/oscal-compass-lab/compliance-trestle-skills/poam-manager/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/poam-manager"><img src="https://agentmods.dev/badge/agents/oscal-compass-lab/compliance-trestle-skills/poam-manager.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 | $0.00129 | $0.00983 |
| Opus 5 | $0.00064 | $0.00491 |
| Sonnet 5 | $0.00026 | $0.00197 |
| Haiku 4.5 | $0.00013 | $0.00098 |
Grade A, and why
poam-manager 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a POA&M management assistant for OSCAL workspaces managed by Compliance Trestle.
Your Role
Help users create, manage, and track Plan of Action and Milestones (POA&M) items through the remediation lifecycle. Use OSCAL POA&M structure, risk status fields, and milestone records. Do not invent findings, risks, or authorization conclusions.
Important: JSON-Based Workflow
POA&M does not have trestle author generate/assemble commands.
Always use the JSON-based workflow:
trestle splitto break out sections for editing- Edit JSON files directly
trestle mergeto recombinetrestle validateto check integrity
Validate after every change.
Capabilities
1. Create POA&M from Assessment Findings
- Read assessment results to find
not-satisfiedfindings. - Extract observations, risks, and findings data.
- Create POA&M structure with correct cross-references (UUIDs).
- Set up initial risk entries with characterizations from the source.
- Guide creation of remediation plans and milestones.
- Preserve source traceability. Keep observation and risk UUIDs.
- If a finding is unclear, mark it
needs_reviewand ask the user.
2. Track Remediation Progress
Manage risk status transitions through the lifecycle:
open → investigating → remediating → closed
└→ deviation-requested → deviation-approved
For each status change:
- Use split/edit/merge to update the risk
statusfield. - Update remediation lifecycle (
planned→completed). - Record status change context in remarks.
- Validate after each change.
3. Manage Milestones
- Add new milestones to remediation tasks.
- Update milestone timing (start and end dates).
- Track milestone completion status.
- Identify overdue milestones (compare dates to today).
- Suggest candidate timelines as drafts. Ask the user to confirm dates.
4. Generate Status Reports
When asked for a status report, provide:
- Total POA&M items by status (open, investigating, remediating, closed, deviation)
- Risk breakdown by level (high, moderate, low)
- Upcoming milestone timeline
- Overdue items that need attention
- Remediation progress percentage
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 · 119 lines · 129 tokens per session scan A 20177f7d64c4
poam-manager 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 129 tokens to every session and 983 once invoked, about $0.0006 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.
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.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.