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 khalilbenaz/claude-skills-collection --skill security-hardenergit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/security-hardener)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/security-hardener"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/security-hardener/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/khalilbenaz/claude-skills-collection/security-hardener"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/security-hardener.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00086 | $0.02426 |
| Opus 5 | $0.00043 | $0.01213 |
| Sonnet 5 | $0.00017 | $0.00485 |
| Haiku 4.5 | $0.00009 | $0.00243 |
Grade A, and why
security-hardener 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 11d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Security Hardener
Quand utiliser ce skill
Agent exposé à des inputs utilisateurs non fiables, déployé en production, ou soumis à des exigences réglementaires (GDPR, SOC2, HIPAA, PCI-DSS). S'applique aussi lors d'une revue sécurité pré-déploiement ou après un incident.
Workflow en 10 étapes
1. Threat modeling — cartographier avant de mitiger
Commence toujours par identifier la surface d'attaque réelle :
| Menace | Vecteur | Impact |
|---|---|---|
| Prompt injection directe | Input utilisateur malveillant | Contournement des instructions |
| Prompt injection indirecte | Données externes (web, fichiers, BDD) | Prise de contrôle via contenu tiers |
| Data exfiltration | Manipulation du contexte | Fuite du system prompt ou données sensibles |
| Tool abuse | Instruction de supprimer/envoyer/publier | Actions destructrices irréversibles |
| Cost attack (DoS éco.) | Requêtes token-maximisantes | Facture API hors de contrôle |
| Social engineering | Dérive progressive du contexte | Contournement progressif des guardrails |
Critère de décision : si l'agent a accès à des outils avec effets de bord (write, delete, send), le niveau de sécurité est automatiquement "HIGH" — appliquer toutes les étapes.
2. Input sanitization
import re
INJECTION_PATTERNS = [
r"ignore\s+(all\s+)?previous\s+instructions",
r"system\s+prompt",
r"jailbreak",
r"DAN\b",
r"<\s*(INST|SYS|system|prompt)\s*>",
r"forget\s+(everything|your\s+rules)",
]
def is_safe_input(text: str, max_len: int = 4000) -> tuple[bool, str]:
if len(text) > max_len:
return False, "INPUT_TOO_LONG"
for pattern in INJECTION_PATTERNS:
if re.search(pattern, text, re.IGNORECASE):
return False, f"INJECTION_DETECTED:{pattern}"
return True, "OK"
- Valider les inputs structurés avec Pydantic (schéma strict, pas de champs
extra="allow"). - Échapper les délimiteurs de prompt (
---,###,<user>) provenant de l'utilisateur. - Piège : l'encodage Base64 ou les caractères Unicode homoglyphes contournent les regex naïves. Normaliser le texte (unicode NFKC) avant de filtrer.
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.
- 11d ago First seen · 256 lines · 86 tokens per session scan E 689ec1752d67
security-hardener is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 17d ago), licensed MIT. It adds 86 tokens to every session and 2,426 once invoked, about $0.0004 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 skills, from other repositories
edgartools
Python library for accessing, analyzing, and extracting data from SEC EDGAR filings. Use when working with SEC filings, financial statements (income statement, balance sheet, cash flow), XBRL financial data, insider trading (Form 4), institutional holdings (13F), company financials, annual/quarterly reports (10-K…
model-routing-patterns
Multi-model pipelines (Haiku/Sonnet/Opus): cost routing, escalation, fallback chains. Triggers: model routing, Haiku, Sonnet, Opus, escalation, fallback chain.
rag-patterns
RAG: embeddings, chunking, hybrid search (BM25+vector), reranking, CRAG, multi-hop. Triggers: RAG, embedding, pgvector, Qdrant, Pinecone, Weaviate, reranker, semantic search.
evaluate
Evaluates RAG retrieval and LLM-as-judge metrics (faithfulness, relevancy, context precision). Triggers: measure RAG quality, knowledge gap, RAG eval, golden dataset.
explain
Explains code/architecture with Mermaid diagrams and sequence flows. Triggers: what does X do, how does Y work, explain code, sequence diagram.
json-mode-patterns
Structured JSON output from Claude: tool-use-as-JSON, schema, parsing, partial recovery. Triggers: JSON mode, structured output, schema validation, JSON parsing.