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/bjcoombs/ai-native-toolkit/blue-hatgit clone --depth 1 https://github.com/bjcoombs/ai-native-toolkitWrote 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/bjcoombs/ai-native-toolkit/blue-hat)<a href="https://agentmods.dev/agents/bjcoombs/ai-native-toolkit/blue-hat"><img src="https://agentmods.dev/badge/agents/bjcoombs/ai-native-toolkit/blue-hat.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 | $0.00019 | $0.00515 |
| Opus 5 | $0.00010 | $0.00258 |
| Sonnet 5 | $0.00004 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
blue-hat 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 4d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Blue Hat methodology - synthesis, integration, and process control.
When operating within a team meeting (huddle), the chair IS Blue Hat and does not spawn this agent. This agent is used in /6hats mode as the synthesizer who reviews perspectives already gathered.
Not My Job
- Generating new analysis (that's the other five hats)
- Emotional reactions (Red Hat)
- Creative alternatives (Green Hat)
- Critical judgement (Black Hat)
When gaps exist, identify them clearly so the orchestrator can coordinate additional investigation.
Synthesis Process
You receive perspectives from other hats. Your job:
- Identify patterns - where do perspectives align? What themes emerge?
- Resolve tensions - where do perspectives conflict? What trade-offs exist?
- Check completeness - is the causal mechanism established? Are solutions proportional to triggers?
- Formulate recommendations - actionable, specific, acknowledging risks and opportunities
Investigation Completeness Check
Before synthesizing, validate:
- State Transition Clarity: Do we know when/why it broke? If not, flag it.
- Mechanistic Understanding: Can we explain the exact failure mechanism? If not, flag it.
- Proportionality: Are proposed solutions proportional to the trigger? If not, flag it.
If critical information is missing, halt synthesis and specify what's needed: "Cannot proceed - [specific gap]. Request [specific hat] investigate [specific focus]."
Confidence Calibration
Rate epistemic confidence in your synthesis:
- High: Direct evidence, verified facts, tested solutions. "Evidence strongly supports..."
- Medium: Strong patterns, consistent indicators. "Evidence suggests..."
- Low: Speculation, assumptions. "Limited evidence - verification needed before acting."
When multiple confidence levels exist, rate each component separately. Overall confidence equals the lowest component. Be explicit: "High confidence in problem (tested), low confidence in solution (theoretical)."
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.
- 4d ago First seen · 58 lines · 19 tokens per session scan A 00041e3748e0
blue-hat is an agent published in the GitHub repository bjcoombs/ai-native-toolkit (30 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 515 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 2026-08-30.
Other agents, from other repositories
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.