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 m-binimran/dev-pack --skill form-buildergit clone --depth 1 https://github.com/m-binimran/dev-packWrote 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/m-binimran/dev-pack/form-builder)<a href="https://agentmods.dev/skills/m-binimran/dev-pack/form-builder"><img src="https://agentmods.dev/badge/skills/m-binimran/dev-pack/form-builder/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/m-binimran/dev-pack/form-builder"><img src="https://agentmods.dev/badge/skills/m-binimran/dev-pack/form-builder.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 | $0.00043 | $0.00347 |
| Opus 5.5 | $0.00017 | $0.00139 |
| Sonnet 5.5 | $0.00009 | $0.00069 |
| Haiku 4.5 | $0.00004 | $0.00035 |
Grade A, and why
form-builder 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.
What it actually says
form-builder
One source of truth for validation (Zod), shared by client and server. Accessible by construction.
Process
- Define the Zod schema once. It validates on the client AND in the server action — no drift.
- React Hook Form + shadcn
Form:useForm({ resolver: zodResolver(schema) }). UseFormField,FormLabel,FormControl,FormMessageso each input is labelled and errors are associated + announced. - Server action does the real validation: re-parse with the same schema in the action; never trust the client.
- States: disabled while submitting, visible loading, success + error feedback (
aria-livefor errors). - Honeypot / basic spam guard on public forms; rate-limit the action.
Accessibility
- Every field has a real
<label>. Errors are text (not color-only) and linked viaaria-describedby. - Submit reachable by keyboard; focus moves to the first error on failed submit.
Output
- The schema, the form component, and the server action — with the shared schema referenced in both.
- Note what validation runs client-side vs. server-side.
Guardrails
- No validation that exists only on the client.
- Don't put secrets/keys in the form component (client code — the
secret-scanhook will block it).
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 · 29 lines · 43 tokens per session scan A 29584384ef8d
form-builder is a skill published in the GitHub repository m-binimran/dev-pack (2 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 347 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
nemo-guardrails
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
token-tracker
Track token consumption, enforce session budgets, and display cost for every NetClaw interaction.
cuga-github-issues
Create GitHub issues for cuga-agent (bugs, features, epics, designs, and related work) against origin using gh, with epic → feature → issue hierarchy and GraphQL sub-issue linking. Use when the user says create new issues, report a bug, file a bug, feature request, new feature, create an epic, GitHub issue, sub-issue…
cuga-contributor-workflows
Run CUGA contributor workflows: Conventional Commits, create pull requests against origin with gh and PR templates, and ruff check/format via uv. Use when the user says commit, create a commit, create PR, pull request, open a PR, ruff check, ruff format, or conventional commits.
agent-safety
Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approval on irreversible actions, capping runtime and cost, or triaging what it already did. NOT building the loop, tools, or…
bluesky-engagement
Automated Bluesky reply monitoring and draft queueing for ThumbGate's acquisition engagement loop. Polls the AT Protocol notifications endpoint every 15 minutes, writes human-reviewable draft replies into a queue file, and never auto-posts without sign-off. Trigger when the user asks about Bluesky replies, engagement…