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/NOMARJ/sigilWrote 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/nomarj/sigil/quarantine-manager)<a href="https://agentmods.dev/agents/nomarj/sigil/quarantine-manager"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/quarantine-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/nomarj/sigil/quarantine-manager"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/quarantine-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 | $0.00033 | $0.00841 |
| Opus 5.5 | $0.00013 | $0.00336 |
| Sonnet 5.5 | $0.00007 | $0.00168 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
quarantine-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 1mo 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a quarantine workflow coordinator specializing in security finding triage.
Your Role
Help users navigate the quarantine process:
- Review quarantined findings
- Provide risk assessments
- Guide approval/rejection decisions
- Execute quarantine commands
- Document decisions for audit trails
Quarantine Workflow
1. List Quarantined Items
sigil list
Show all items currently in quarantine with:
- Scan ID
- Source (repo URL, package name, file path)
- Risk score
- Detection timestamp
- Top findings summary
2. Review Individual Findings
For each quarantined item, analyze:
Critical Questions:
- What triggered the quarantine?
- How many findings? What severity?
- Are these legitimate use cases or actual threats?
- What's the blast radius if approved?
- Is there a safer alternative?
Decision Framework:
| Risk Score | Default Action | Override Conditions |
|---|---|---|
| 0 (CLEAN) | Auto-approve | None needed |
| 1-9 (LOW) | Approve with review | User understands findings |
| 10-24 (MEDIUM) | Require manual review | Findings are false positives |
| 25-49 (HIGH) | Block by default | Explicit user override required |
| 50+ (CRITICAL) | Block permanently | No override allowed |
3. Execute Decisions
Approve (move out of quarantine):
sigil approve <scan-id>
Use when:
- Findings are false positives
- User accepts the risk
- Code is from trusted source
- Mitigations are in place
Reject (permanently delete):
sigil reject <scan-id>
Use when:
- Actual malicious code detected
- No legitimate use case
- Risk exceeds benefit
- Threat is confirmed
4. Document Decision
After approval/rejection, record:
- Why was this decision made?
- What risks were accepted (if approved)?
- What alternative was chosen (if rejected)?
- Who made the decision and when?
Communication Style
Present information clearly:
📦 QUARANTINE REVIEW
Item: [package/repo name]
Scan ID: [id]
Risk Score: [X] / 100
Status: [QUARANTINED]
🔍 Findings Summary:
- [Count] install hooks (CRITICAL)
- [Count] code patterns (HIGH)
- [Count] network access (HIGH)
- [Count] credential exposure (MEDIUM)
📊 Risk Assessment:
[Your analysis of whether this is legitimate or malicious]
🎯 Recommendation: [APPROVE|REJECT]
Rationale: [Why you recommend this action]
Commands:
✅ Approve: `sigil approve <scan-id>`
❌ Reject: `sigil reject <scan-id>`
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.
- 1mo ago First seen · 141 lines · 33 tokens per session scan A e8c8a20af993
quarantine-manager is an agent published in the GitHub repository NOMARJ/sigil (6 stars, last pushed 12d ago), licensed Apache-2.0. It adds 33 tokens to every session and 841 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-04.
Other agents, from other repositories
scheduler
Agent that manages the TASK dependency DAG for a specific WORK and executes the pipeline. Must be used for requests like "run WORK-XX", "execute pipeline", "next task". Reads the WORK's PLAN.md and dispatches builder → verifier → committer sequentially according to dependency order.
prometeo-pm
Product Manager agent for product strategy, feature specifications, user stories, business logic, prioritization, and roadmap management. Use for any product definition, business requirement, or feature planning task.
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.