Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jeffsenso/prestashop-skillsnpx agentmods add skills/jeffsenso/prestashop-skills/create-skillWrote 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/jeffsenso/prestashop-skills/create-skill)<a href="https://agentmods.dev/skills/jeffsenso/prestashop-skills/create-skill"><img src="https://agentmods.dev/badge/skills/jeffsenso/prestashop-skills/create-skill/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/jeffsenso/prestashop-skills/create-skill"><img src="https://agentmods.dev/badge/skills/jeffsenso/prestashop-skills/create-skill.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 | $0.00057 | $0.02170 |
| Opus 5 | $0.00028 | $0.01085 |
| Sonnet 5 | $0.00011 | $0.00434 |
| Haiku 4.5 | $0.00006 | $0.00217 |
Grade A, and why
create-skill 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 9d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a New Skill
Where to place it
Choose the location based on scope — in order of priority:
| Priority | Condition | Path |
|---|---|---|
| 1 | User explicitly provided a path | Use that path |
| 2 | Skill is tied to a specific component | .ai/Component/{Name}/skills/{skill-name}/SKILL.md |
| 3 | Skill is tied to a specific domain | .ai/Domain/{Name}/skills/{skill-name}/SKILL.md |
| 4 | Cross-cutting (spans multiple domains/components) | .ai/skills/{skill-name}/SKILL.md |
After writing the file:
- Add a
## Skillssection (or entry) to the correspondingCONTEXT.md— root.ai/CONTEXT.mdfor cross-cutting skills, or.ai/Component/{Name}/CONTEXT.md/.ai/Domain/{Name}/CONTEXT.mdfor scoped skills. This is the agnostic discovery mechanism for all non-Claude tools. - Create a symlink in
.claude/skills/pointing to the skill directory (not the file). The path must be relative. This enables Claude Code auto-discovery.cd .claude/skills && ln -s ../../<skill-dir-path-from-repo-root> <skill-name>
CONTEXT.md vs SKILL.md — no duplication rule
CONTEXT.md owns conventions (rules, patterns, constraints — the "why" and "what"). SKILL.md owns procedures (steps, code templates, checklists — the "how"). Content must live in exactly one place.
| CONTEXT.md | SKILL.md | |
|---|---|---|
| Contains | Conventions, rules, patterns | Procedures, step-by-step instructions, code templates |
| Audience | Any AI tool or human | An AI agent executing a specific task |
| Duplication | Authoritative source — never restated elsewhere | References CONTEXT.md conventions, never restates them |
When creating or modifying a skill
For every rule or convention you're about to write in a skill, apply this decision:
- Read the parent CONTEXT.md first — before writing any content in a skill, read the component (or domain) CONTEXT.md to know what's already documented there
- Ask: "Does this apply to all skills in this component?" — if yes, it belongs in CONTEXT.md, not the skill. Example: "all handlers use
#[AsCommandHandler]" → CONTEXT.md - Ask: "Is this specific to this one task?" — if yes, it stays in the skill. Example: "the edit handler checks null before each field" → skill
- If a convention is missing from CONTEXT.md and should be there — add it to CONTEXT.md first, then reference it from the skill. Never write it only in the skill
- Reference, don't restate — when a skill needs to remind the reader of a convention, write:
See [Component/CONTEXT.md](../../CONTEXT.md#section) for X convention.Do not copy the rule text into the skill
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.
- 9d ago First seen · 164 lines · 57 tokens per session scan A 798b2744a0c1
create-skill is a skill published in the GitHub repository jeffsenso/prestashop-skills (5 stars, last pushed 14d ago), licensed MIT. It adds 57 tokens to every session and 2,170 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
810-regulations-eu-mifid-ii
Use when reviewing Java enterprise evidence for MiFID II investment services, investment activities, client classification, suitability, appropriateness, order-handling evidence, best-execution evidence, algorithmic-trading governance evidence, market-access governance evidence, transaction evidence, record keeping…
812-regulations-eu-product-liability-directive
Use when reviewing, designing, or modifying Java enterprise software products, AI-enabled products, RAG assistants, AI agents, generated instructions, related services, automated updates, vulnerability handling, corrective updates, warnings, instructions, or product-safety evidence under Directive (EU) 2024/2853, the…
801-regulations-eu-ai-act
Use when reviewing, designing, or modifying Java enterprise systems that use AI, LLMs, AI agents, RAG, tool calling, workflow automation, or model-based decision support and need EU AI Act regulatory awareness. This should trigger for requests such as Review a Java AI system for EU AI Act controls; Design governance…
802-regulations-dora
Use when reviewing, designing, or modifying Java enterprise systems that may support financial entities, critical ICT services, third-party ICT provider integrations, or operational resilience obligations under DORA. This should trigger for requests such as Review a Java platform for DORA ICT risk controls; Design…
803-regulations-gdpr
Use when reviewing, designing, or modifying Java enterprise systems that process personal data and need GDPR-aware engineering controls. This should trigger for requests such as Review a Java service for GDPR privacy controls; Design data-subject rights workflows; Add retention, deletion, pseudonymization, or…
042-planning-openspec
Use when creating or updating OpenSpec artifacts from an issue, plan, approved design, ADRs, existing OpenSpec, or a valid combination. The workflow assesses reviewable scope, records source authority and derivation, handles conflicts, and prevents silent synchronization. Triggers include Create OpenSpec from an…