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 qaml-ai/camelAI --skill developing-softwaregit clone --depth 1 https://github.com/qaml-ai/camelAIWrote 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/qaml-ai/camelai/developing-software)<a href="https://agentmods.dev/skills/qaml-ai/camelai/developing-software"><img src="https://agentmods.dev/badge/skills/qaml-ai/camelai/developing-software/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/qaml-ai/camelai/developing-software"><img src="https://agentmods.dev/badge/skills/qaml-ai/camelai/developing-software.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 | $0.00085 | $0.01707 |
| Opus 5.5 | $0.00034 | $0.00683 |
| Sonnet 5.5 | $0.00017 | $0.00341 |
| Haiku 4.5 | $0.00009 | $0.00171 |
Grade A, and why
developing-software 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developing Software
Read this file completely once per task before the first create_project call. Do not reread it during the same task unless the instructions change. Read a reference below with read_skill({ skill: "developing-software", file: "<filename>" }); do not use the generic project/workspace file tools for skill files.
Workflow
- Choose the template for the dominant user experience.
- Create the project with a concise description and an explicit
template. - Inspect the seeded files before editing. Treat the scaffold as working architecture, not disposable sample code.
- Reshape the starter into the requested product. Rename the example entity, schema, routes, actions, validation, and UI copy consistently instead of adding a second implementation beside the demo.
- In React Router projects, add standard UI through
add_shadcn_component; do not hand-write components or page shells that the bundled registry provides. Invanillaprojects, work directly inpublic/. - Use
deploy_projectdirectly to build, publish, return the live URL, and open the app in preview. No manualset_previeworlist_appscall is needed afterward;set_previewremains available when you explicitly want to reopen or switch previews. Passdry_run: trueonly when the user explicitly wants validation without publishing. - Treat a successful deploy as sufficient completion evidence for routine build-and-ship requests. Do not automatically launch
env.BROWSERor capture screenshots after every deploy. Use browser or visual verification only when the user asks for it, the task is specifically diagnosing a deployed UI/runtime issue, or the task explicitly requires browser evidence.
Use camelAI project tools for scaffolding, dependencies, builds, and deploys. Do not run create-worker, wrangler init, npm create cloudflare, package-manager deploy commands, or shell-based scaffolding.
Template Selection
| Template | Choose when |
|---|---|
crud |
The product is primarily a stateful app, admin tool, tracker, portal, or workflow. This is the default and includes React Router loaders/actions plus Durable Object SQLite CRUD. |
vanilla |
The experience is client-only plain HTML/CSS/JavaScript: a small site, landing page, calculator, quiz, interactive demo, or simple DOM/canvas game. Prefer crud when it needs accounts, durable server records, a shared leaderboard, or multiplayer state. |
ai-chat |
Conversation or direct model interaction is the primary experience. An otherwise stateful app with one AI-assisted feature should normally remain crud and add the AI binding. |
integration-dashboard |
Discovering, monitoring, or operating workspace-connected SaaS/database services is central. If connections only provide business metrics, prefer data-dashboard. |
data-dashboard |
Users interact with KPIs, filters, charts, tables, exports, or drill-downs. |
data-analysis |
The deliverable is a notebook-first, read-only analytical report. Use the data-analysis skill and run_notebook; do not treat it like a React app. |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 93 lines · 85 tokens per session scan A 0f03a7ab13d9
developing-software is a skill published in the GitHub repository qaml-ai/camelAI (390 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 1,707 once invoked, about $0.0003 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.
Other skills, from other repositories
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.
django-storages-s3
Use when configuring Django to store static and media files on AWS S3 with django-storages. Invoke when working with the STORAGES setting, S3 buckets, presigned URLs, CloudFront, or boto3-backed file storage in settings.py. Configures the Django 4.2+ STORAGES dict, public/private custom backends, presigned GET/POST…
websocket-engineer
Use when building real-time communication systems with WebSockets or Socket.IO. Invoke for bidirectional messaging, horizontal scaling with Redis, presence tracking, room management.
azure-eventhub-dotnet
Azure Event Hubs SDK for .NET. Use for high-throughput event streaming: sending events (EventHubProducerClient, EventHubBufferedProducerClient), receiving events (EventProcessorClient with checkpointing), partition management, and real-time data ingestion. Triggers: "Event Hubs", "event streaming"…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
aws-blocks
Guides building full-stack applications with AWS Blocks — an Infrastructure-from-Code framework. Applies when creating APIs, selecting Building Blocks (KVStore, DistributedTable, Database, AuthBasic, AuthCognito, Realtime, AsyncJob, FileBucket, etc.), running local development, or deploying AWS Blocks applications.…