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/white-hatgit clone --depth 1 https://github.com/bjcoombs/ai-native-toolkitWhat 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 | $0.00022 | $0.00574 |
| Opus 5 | $0.00011 | $0.00287 |
| Sonnet 5 | $0.00004 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
white-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 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply White Hat methodology - objective facts, evidence, and verified claims.
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
- Critical judgement (Black Hat)
- Emotional reactions (Red Hat)
- Creative alternatives (Green Hat)
- Celebrating benefits (Yellow Hat)
LIMITED CHOICE BIAS DETECTION
When detecting constrained choice sets (2-4 options):
- Document the constrained set as presented
- Investigate beyond: root causes, adjacent solutions, cross-domain options, constraint origins, null hypothesis
- Question: "What assumptions make these the only choices?"
- Report discovered options outside the original framing
- Show search commands that explored beyond the constraints
Contextual Discovery
Before investigating, ask: "What domain-specific facts might matter here that I haven't considered?" Identify unique domain considerations (regulatory, safety, scale, latency, compliance) and link to specific evidence.
Code-First Investigation
Principle: Ground all findings in actual code evidence and specific locations. Investigation first, analysis second.
- Find the code - show actual search commands used
- Show the implementation - include real code with file:line references
- Then analyse - only after evidence is established
If code doesn't exist, state clearly: "No existing implementation found" with the search commands you ran.
Claims without evidence are not White Hat findings. Show the search, show the code, then draw conclusions.
State Transition Analysis
When investigating "it used to work" scenarios:
- "When did it last work?" - establish baseline
- "What changed between then and now?" - find the trigger
- "What made existing code fail?" - identify activation mechanism
State Transition Evidence:
- Last working: [date/version]
- First failure: [date/version]
- Changes between: [actual diff or commit log]
- Activation trigger: [what made latent issue manifest]
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.
- 2d ago First seen · 70 lines · 22 tokens per session scan A d81b9cf863b0
white-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 22 tokens to every session and 574 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
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
shep-web-route-creator
Scaffolds ONE new Next.js API route under src/presentation/web/app/api/, wires it to an existing use case via resolve(), handles the canonical error-to-HTTP mapping, and keeps presentation thin. Use when a use case already exists and the caller needs a web endpoint exposing it. Does NOT create the use case, does NOT…
python-pro
Python 3.13 language expert for the ClosedLoop plugin monorepo. Reviews implementation plans for type annotation correctness, argparse CLI conventions, import isolation, fail-open/fail-closed boundary patterns, and pyright/ruff compliance. Produces type-patterns.md in legacy mode.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…