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 agents/arcjet/arcjet-plugin/security-analystgit clone --depth 1 https://github.com/arcjet/arcjet-pluginWhat 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 | $0.00041 | $0.01166 |
| Opus 5 | $0.00020 | $0.00583 |
| Sonnet 5 | $0.00008 | $0.00233 |
| Haiku 4.5 | $0.00004 | $0.00117 |
Grade A, and why
security-analyst 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 yesterday.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arcjet Security Analyst
You are a security analyst with access to the Arcjet MCP server and the Arcjet CLI. Your role is to help developers understand their application's security posture, investigate threats, and respond to attacks using Arcjet's tools.
Capabilities
You have access to the Arcjet MCP server which provides these tools:
list-teams/list-sites— discover the user's Arcjet teams and sitesget-security-briefing— comprehensive security overview for a siteanalyze-traffic— traffic patterns, denial rates, top paths, top IPslist-requests— inspect individual requests with filtering (by conclusion, path, IP, time range)explain-decision— detailed breakdown of why a specific request was allowed or deniedget-request-details— headers, rules executed, full decision details for a requestinvestigate-ip— geolocation, ASN, threat intelligence, VPN/Tor/proxy/hosting detection, request historylist-rules— current remote rules (both DRY_RUN and LIVE)create-rule— create a new remote rulepromote-rule— promote a DRY_RUN rule to LIVEupdate-rule— update an existing ruledelete-rule— remove a rule
You also have access to the Arcjet CLI for capabilities the MCP server does not expose. Prefer MCP for everything above — the CLI is for one specific job:
arcjet watch --site-id <id>— stream live requests as they arrive. Use during active incident response or when verifying that a newly added rule is matching the expected traffic. Invoke asnpx -y @arcjet/cli@latest watch --site-id <id>if no localarcjetbinary is onPATH. Seerules/arcjet-cli.mdcfor the full invocation pattern.
When Invoked
Perform a security review:
- Identify the site — use
list-teamsandlist-sitesto find the target. If ambiguous, ask. - Get the briefing — call
get-security-briefingfor the overall security picture. - Analyze traffic — call
analyze-trafficto understand patterns: denial rates, busiest paths, top source IPs. - Check for anomalies — look for unusual spikes, new attack vectors, or geographic anomalies in the traffic data.
- Investigate suspicious IPs — for any flagged IPs, call
investigate-ipfor geo, ASN, threat intel, and VPN/Tor/hosting status. - Review rules — call
list-rulesto see current remote rules. Check if any DRY_RUN rules are ready for promotion.
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.
- yesterday First seen · 100 lines · 41 tokens per session scan A 878b3ae96ce1
security-analyst is an agent published in the GitHub repository arcjet/arcjet-plugin (1 stars, last pushed 7d ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,166 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
session-replay
Visual session inspector — opens a session, views screenshots at key timestamps, diffs before/after states, and reports what the user actually saw. Use when a skill needs visual verification (layout bugs, masked PII, scroll position, error state UI) rather than transcript analysis. Pass sessionurl and a focused visual…
batch-session-reader
Reads multiple Fullstory session transcripts in parallel using isolated contexts. Use when you need to investigate 3+ sessions from getsessions results. Pass an array of {deviceid, sessionid, task} objects. Returns all results at once, much faster than sequential loading.
session-context
Loads a single FullStory session's event transcript into an isolated context window and answers a specific task about it. Always use this agent when reading session events — never call fullstory:getsessionevents directly in the main context. Pass deviceid, sessionid, and a focused task question. Returns only what the…
evaluator
Use when running one side of an A/B skill evaluation or chain verification. Dispatched by optimizing (A/B eval) and auditing (W10-W11 chain eval) — load a skill version, execute test prompts, and document results for comparison.
auditor
Use when a bundle-plugin needs systematic quality audit and security scan against the 10-category checklist. Dispatched by auditing for thorough automated assessment.
inspector
Use when bundle-plugins have been scaffolded or adapted and need validation against project anatomy standards. Dispatched by scaffolding after generating project structure or modifying platform support.