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/green-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 | $0.00018 | $0.00563 |
| Opus 5 | $0.00009 | $0.00282 |
| Sonnet 5 | $0.00004 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
green-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 3d 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 Green Hat methodology - creative thinking that explores the full solution space.
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
- Risk analysis and critique (Black Hat)
- Emotional reactions (Red Hat)
- Fact verification (White Hat)
- Celebrating benefits (Yellow Hat)
LIMITED CHOICE TRANSCENDENCE
Frame Audit Protocol (run before generating alternatives):
- Choice Set Analysis: What do the presented options have in common?
- Assumption Mining: What assumptions make these "the only" choices?
- Problem Inversion: What if we did the OPPOSITE of all options?
- Domain Jumping: How would other industries solve this?
- Constraint Elimination: What if the forcing constraint vanished?
The "Option Z" Principle: Always include "Option Z: Make this problem disappear" beyond any presented options.
Creative Expansion Tiers
Tier 1 - Within-Frame (staying in the box):
- Combine, resequence, or partially implement existing options
- Simpler alternatives: modify existing code, change SQL, adjust config
Tier 2 - Adjacent (expanding the box):
- Options 5, 6, 7 that weren't presented
- Hybrid approaches, solutions from similar domains
Tier 3 - Frame-Breaking (destroying the box):
- Challenge why we need ANY of these options
- Solutions from completely different domains
- Make the problem structurally impossible
- Turn the constraint into the solution
Explore ALL tiers. Simple solutions and creative complexity both have their place - the problem determines which is right.
Contextual Creative Discovery
Before generating solutions, ask: "What domain-specific creative patterns exist here?" What unique solution patterns work in this domain? What constraints can become features?
The Lazy Developer (One Tool, Not the Only Tool)
Quick check before going deeper:
- "What's the 5-minute fix?"
- "What requires zero new dependencies?"
- "Why can't we just modify existing code?"
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.
- 3d ago First seen · 70 lines · 18 tokens per session scan A 0ff7614972dc
green-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 18 tokens to every session and 563 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…