Borrowing it
Nothing to install: this file belongs to veryfront/veryfront-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/veryfront/veryfront-code/main/.claude/skills/vf-ext-development/SKILL.mdgit clone --depth 1 https://github.com/veryfront/veryfront-codeWrote 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/veryfront/veryfront-code/vf-ext-development)<a href="https://agentmods.dev/skills/veryfront/veryfront-code/vf-ext-development"><img src="https://agentmods.dev/badge/skills/veryfront/veryfront-code/vf-ext-development/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/veryfront/veryfront-code/vf-ext-development"><img src="https://agentmods.dev/badge/skills/veryfront/veryfront-code/vf-ext-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 290 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Prompt Injection · line 299 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00041 | $0.03824 |
| Opus 5.5 | $0.00016 | $0.01530 |
| Sonnet 5.5 | $0.00008 | $0.00765 |
| Haiku 4.5 | $0.00004 | $0.00382 |
Grade A, and why
vf-ext-development 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 2mo 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Veryfront Extension Development
Overview
A Veryfront extension is a deno.json-described package that default-exports an ExtensionFactory. The factory returns an object that declares its contracts, declares its capabilities, and optionally provides implementations through static provides or dynamic setup(ctx).
Core principle: The manifest and the factory must agree. CI fails the build if veryfront.contracts / veryfront.capabilities in deno.json drift from what the factory returns.
When to Use
- Creating a new extension under
extensions/ - Adding/removing a contract or capability on an existing extension
- Adding a new contract type to the framework (also touches the recommendations registry and the extensions README)
- Writing tests for an extension factory or its contract implementation
- Triaging
lint:extension-contracts/lint:extension-capabilitiesfailures
Scaffold
veryfront extension init ext-my-cache # writes extensions/ext-my-cache/{deno.json,src/index.ts,src/index.test.ts}
veryfront extension validate extensions/ext-my-cache
Always use the ext- prefix. scripts/lint/audit-extension-{capabilities,contracts}.ts only scan directories whose name starts with ext-; an extension at extensions/my-cache/ is silently skipped by both lint tasks. veryfront extension init does not add the prefix for you — pass it explicitly.
Package Structure
extensions/ext-<name>/
├── deno.json # Manifest — name, contracts, capabilities, imports
├── README.md # Required for first-party extensions
└── src/
├── index.ts # Default-exported ExtensionFactory
├── index.test.ts # Factory + setup/teardown tests
└── <impl>.ts # Implementation modules + colocated *.test.ts
Manifest (deno.json)
{
"name": "@veryfront/ext-cache-redis",
"version": "0.1.0",
"exports": "./src/index.ts",
"veryfront": {
"extension": true,
"contracts": { "provides": ["TokenCacheStore"], "requires": [] },
"capabilities": [
{ "type": "net:outbound", "hosts": ["*"] },
{ "type": "env:read", "keys": ["REDIS_URL", "REDIS_PREFIX", "REDIS_PASSWORD"] }
]
},
"imports": {
"redis": "npm:[email protected]",
"veryfront/extensions": "../../src/extensions/index.ts",
"veryfront/extensions/cache": "../../src/extensions/cache/index.ts"
}
}
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.
- 2mo ago First seen · 325 lines · 41 tokens per session scan A 2d49cb9bc344
vf-ext-development is a skill published in the GitHub repository veryfront/veryfront-code (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 3,824 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 2026-08-30.
vf-ext-development compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vf-ext-developmentveryfront/veryfront-code | Skill | 20 | yesterday | Apache-2.0 | A | 41 | Claude Code |
| chatbotericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 78 | Claude Code, Codex |
| axwiseAxWise-GmbH/axwise-flow | Skill | 62 | yesterday | Apache-2.0 | A | 93 | Claude Code, Codex |
| contractAbyssCN/oh-my-dag | Skill | 44 | 26d ago | MIT | A | 102 | Claude Code, Codex |
| omd-videoAbyssCN/oh-my-dag | Skill | 44 | 26d ago | MIT | A | 158 | Claude Code, Codex |
| grillAbyssCN/oh-my-dag | Skill | 44 | 26d ago | MIT | A | 116 | Claude Code, Codex |
| omd-research-deepAbyssCN/oh-my-dag | Skill | 44 | 26d ago | MIT | A | 120 | Claude Code, Codex |