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.
npx agentmods add commands/postrv/narsil-mcp/security-scangit clone --depth 1 https://github.com/postrv/narsil-mcpWrote 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/commands/postrv/narsil-mcp/security-scan)<a href="https://agentmods.dev/commands/postrv/narsil-mcp/security-scan"><img src="https://agentmods.dev/badge/commands/postrv/narsil-mcp/security-scan.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.00292 |
| Opus 5 | $0.00005 | $0.00146 |
| Sonnet 5 | $0.00002 | $0.00058 |
| Haiku 4.5 | $0.00001 | $0.00029 |
Grade A, and why
security-scan 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 5d 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.
What it actually says
Security Scan
Run a comprehensive security audit on the repository specified by the user. If no repository is specified, first use list_repos to show available repositories and ask which one to scan.
Workflow
Execute the following steps:
-
Get security overview: Use
get_security_summaryto get an overview of the security posture -
Scan for vulnerabilities: Use
scan_securitywithseverity_threshold="medium"to find medium and above findings -
Check OWASP Top 10: Use
check_owasp_top10to check for web application vulnerabilities -
Check dependencies: Use
check_dependenciesto find known CVEs in dependencies -
Check licenses: Use
check_licensesto identify license compliance issues -
Summarize findings: Present a summary organized by:
- Critical/High severity findings (immediate attention needed)
- Medium severity findings (should address soon)
- Dependency vulnerabilities with available fixes
- License issues
-
For each critical finding: Use
explain_vulnerabilityto provide context andsuggest_fixto show remediation
Arguments
If $ARGUMENTS is provided, use it as the repository name. Otherwise, list available repositories first.
Repository to scan: $ARGUMENTS
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.
- 5d ago First seen · 36 lines · 9 tokens per session scan A 9abb0713755a
security-scan is a command published in the GitHub repository postrv/narsil-mcp (181 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 9 tokens to every session and 292 once invoked, about $0.0000 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 commands, from other repositories
localnest:recall
Recall relevant memories for the current task or query.
localnest:remember
Save a decision, fact, or learning to LocalNest memory.
localnest:search
Search codebase and memory via LocalNest.
localnest:prime
Get full task context — memories, entities, files, changes, and actions in one call.
localnest:teach
Teach your AI a durable behavior rule that persists across sessions.
localnest:context
Get full task context — runtime status + recalled memories in one call.