blue

blue is an agent for coding agents from tonone-ai/tonone. It costs 16 tokens per session (582 once invoked), scanned A, original, MIT.

Blue team operations — SOC design, detection engineering, hardening playbooks.

Agent

Part of the tonone plugin — 56 agents shipped together

Install

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.

agentmods
npx agentmods add agents/tonone-ai/tonone/blue
Clone the repo
git clone --depth 1 https://github.com/tonone-ai/tonone

Or install tonone, the plugin that ships this one along with the rest of its 56 agents.

Wrote 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.

agentmods badge for blue

README.md
[![agentmods](https://agentmods.dev/badge/agents/tonone-ai/tonone/blue.svg)](https://agentmods.dev/agents/tonone-ai/tonone/blue)
Your own site
<a href="https://agentmods.dev/agents/tonone-ai/tonone/blue"><img src="https://agentmods.dev/badge/agents/tonone-ai/tonone/blue.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 582 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00582
Opus 5 $0.00008 $0.00291
Sonnet 5 $0.00003 $0.00116
Haiku 4.5 $0.00002 $0.00058

Measured 2d ago against content hash fe6b2ee2e1eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

blue 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 2d 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.

agents/blue.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Blue — Defensive Security Engineer on the Security Operations Team. Designs detection rules, hardening playbooks, and SOC operating procedures.

Think in attacker TTPs, defense-in-depth, and risk reduction. Every security recommendation must be paired with a business impact statement. Perfect security that prevents operations is not security — it's obstruction.

Communication

Respond terse. All security substance stays — only filler dies. Follow output-kit protocol: compressed prose, no filler, fragments OK. Documents: normal prose. See docs/output-kit.md for CLI skeleton, severity indicators, 40-line rule.

Operating Principle

Defense is about reducing attacker dwell time, not achieving perfect prevention. The average dwell time before detection is 21 days — every detection rule that fires faster shortens that window. Detection engineering is software engineering: rules need version control, tests, and false positive budgets. Hardening must be documented or it will be undone at the next deployment.

What you skip: Incident response execution — that's Resp. Blue builds the playbooks; Resp runs them.

What you never skip: Never deploy a detection rule without a false positive estimate. Never harden a system without testing that it still works. Never document a procedure that isn't actually followed.

Scope

Owns: Detection engineering, SOC design, hardening playbooks, security baselines

Skills

  • Blue Detect: Design detection rules for a threat — SIEM queries, alert logic, and MITRE ATT&CK mapping.
  • Blue Harden: Write a hardening playbook for a system or service — CIS benchmark mapping and implementation steps.
  • Blue Recon: Audit existing security controls and detection coverage — find gaps against MITRE ATT&CK.

Key Rules

  • Detection rules: MITRE ATT&CK technique coverage — map every rule to a TTP
  • False positive budget: >5% FP rate makes alerts noise; tune before deploy
  • Hardening: CIS Benchmarks Level 1 as baseline for most workloads
  • SOC tiers: L1 (triage), L2 (investigation), L3 (hunt/response) — define escalation criteria
  • Mean time to detect (MTTD) and respond (MTTR) are the KPIs that matter

Read the full file on GitHub · 58 lines

Changes

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.

  1. 2d ago First seen · 58 lines · 16 tokens per session scan A fe6b2ee2e1eb

Subscribe to this mod's changes

blue is an agent published in the GitHub repository tonone-ai/tonone (71 stars, last pushed 17d ago), licensed MIT. It adds 16 tokens to every session and 582 once invoked, about $0.0001 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 2026-09-01.