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 skills add smicolon/ai-kit --skill security-first-validatorgit clone --depth 1 https://github.com/smicolon/ai-kitWrote 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/skills/smicolon/ai-kit/security-first-validator)<a href="https://agentmods.dev/skills/smicolon/ai-kit/security-first-validator"><img src="https://agentmods.dev/badge/skills/smicolon/ai-kit/security-first-validator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/smicolon/ai-kit/security-first-validator"><img src="https://agentmods.dev/badge/skills/smicolon/ai-kit/security-first-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00056 | $0.02585 |
| Opus 5.5 | $0.00022 | $0.01034 |
| Sonnet 5.5 | $0.00011 | $0.00517 |
| Haiku 4.5 | $0.00006 | $0.00259 |
Grade A, and why
security-first-validator 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 1mo 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 — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security-First Validator
Enforces security requirements for all Django REST Framework API endpoints.
Activation Triggers
This skill activates when:
- Creating API views or viewsets
- Creating serializers
- Mentioning "endpoint", "API", "view", "route"
- Writing DRF classes (APIView, ViewSet, Serializer)
- Creating URL patterns for APIs
- Discussing authentication or permissions
Security Requirements (MANDATORY)
Every API endpoint MUST have:
1. Permission Classes (REQUIRED)
from rest_framework import viewsets
from rest_framework.permissions import IsAuthenticated
class UserViewSet(viewsets.ModelViewSet):
permission_classes = [IsAuthenticated] # ✅ REQUIRED
# ...
2. Serializer Validation (REQUIRED)
from rest_framework import serializers
class UserSerializer(serializers.ModelSerializer):
class Meta:
model = User
fields = ['id', 'email', 'first_name']
# NO sensitive fields exposed ✅
def validate_email(self, value):
# Custom validation ✅
if not value.endswith('@company.com'):
raise serializers.ValidationError("Must use company email")
return value
3. No Raw SQL (REQUIRED)
# ❌ DANGEROUS
User.objects.raw(f"SELECT * FROM users WHERE id = {user_id}")
# ✅ SAFE
User.objects.filter(id=user_id)
4. Rate Limiting (REQUIRED for sensitive endpoints)
from rest_framework.throttling import UserRateThrottle
class LoginView(APIView):
throttle_classes = [UserRateThrottle] # ✅ REQUIRED for auth
# ...
Validation Process
Step 1: Detect New API Endpoint
When API code is being written:
class UserViewSet(viewsets.ModelViewSet):
queryset = User.objects.all()
serializer_class = UserSerializer
# Missing security! ❌
Step 2: Run Security Checklist
Verify:
- ✅ Permission classes defined
- ✅ Serializer has proper validation
- ✅ No raw SQL queries
- ✅ Rate limiting on sensitive endpoints
- ✅ No password/token fields in serializer
- ✅ Proper CORS configuration
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.
- 1mo ago First seen · 436 lines · 56 tokens per session scan A 670f9e285dfc
security-first-validator is a skill published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 2,585 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
add-dial-tool
Give chosen NanoClaw agents a real phone number as a container tool — the dial CLI baked into the agent image plus OneCLI credential injection for api.getdial.ai, attached only to the agents you pick, so they can send SMS, place AI voice calls, and receive verification codes from inside the sandbox. Independent of the…
add-telegram
Add Telegram channel integration via Chat SDK.
add-gchat
Add Google Chat channel integration via Chat SDK.
add-signal
Add Signal channel integration via signal-cli device-link. Native adapter — no Chat SDK bridge.
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
onecli-gateway
OneCLI Gateway: transparent HTTPS proxy that injects stored credentials into outbound calls. You MUST use this skill when the user asks you to read emails, check calendar, access GitHub repos, create issues, check Stripe payments, or interact with ANY external service or API. Do NOT use browser extensions or OAuth CLI…