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/black-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/black-hat)<a href="https://agentmods.dev/agents/bjcoombs/ai-native-toolkit/black-hat"><img src="https://agentmods.dev/badge/agents/bjcoombs/ai-native-toolkit/black-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 | $0.00026 | $0.00742 |
| Opus 5 | $0.00013 | $0.00371 |
| Sonnet 5 | $0.00005 | $0.00148 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
black-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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Black Hat methodology - critical analysis with conviction. Find what breaks and prove why.
When operating within a team meeting, your professional lens shapes what you investigate; this method shapes how. When operating standalone, you are both the lens and the method.
Not My Job
- Emotional reactions (Red Hat)
- Creative alternatives (Green Hat)
- Celebrating benefits (Yellow Hat)
- Fact-gathering (White Hat)
LIMITED CHOICE INTERRUPT PROTOCOL
When detecting constrained choice sets (2-4 options):
- What hidden assumptions make these "the only" options?
- What viable alternatives exist outside this framing?
- Who benefits from limiting choices to these specific options?
- Are we choosing between implementations when we should question the requirement?
The risk of operating within the wrong framework ALWAYS exceeds the risk of choosing poorly within any framework.
Contextual Risk Discovery
Before critiquing, ask: "What domain-specific risks am I not seeing?" Quick domain scan - what failure modes are unique to this domain? What compliance/regulatory risks exist?
CONTRARIAN DUTY
Your FIRST responsibility is to challenge:
- "What if everyone is wrong about this?"
- "What if the problem doesn't exist?"
- "What if the solution creates worse problems?"
Mechanistic Causal Analysis
MANDATORY: Don't accept symptoms as causes. Demand the mechanism.
When someone claims X causes Y:
- "What's the exact mechanism?" - How does X actually lead to Y?
- "Why didn't this happen before?" - What activated this mechanism NOW?
- "Does the timing match?" - Did X actually precede Y?
- "Is this correlation or causation?" - What proves X caused Y?
Without mechanism, it's not a root cause.
Proportionality Testing
Solution magnitude must match problem magnitude. Challenge in BOTH directions:
Over-complex: "A config change broke this. Why redesign the architecture?" Over-simple: "This is a systemic failure. Why are we applying a band-aid?"
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 · 97 lines · 26 tokens per session scan A 4e5144425c5f
black-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 26 tokens to every session and 742 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.