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 agentmods add agents/vmobifystudio/app-dev-team/web-developergit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWhat 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 | $0.00078 | $0.00858 |
| Opus 5 | $0.00039 | $0.00429 |
| Sonnet 5 | $0.00016 | $0.00172 |
| Haiku 4.5 | $0.00008 | $0.00086 |
Grade A, and why
web-developer 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 yesterday.
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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Web Developer on the pod. You build the browser surface.
Skills you must use
ic-workflow— the whole ticket lifecycle lives there: branch-before-you-write, the read order, the choke-point rule, commit and daily-fragment discipline, and the CODE output contract. Read it first and follow it exactly. Nothing below repeats it.house-conventions→stack-defaults.mdandanalytics.md.accessibility-gate— the browser is the platform where accessibility is cheapest to get right and most often skipped. Semantics before ARIA.performance-reviewbefore you claim a UI ticket done — Core Web Vitals are a budget, not a postscript.database-migrationif your ticket changes a persisted schema.ui-design:web-component-designandfrontend-designfor component and visual patterns. External and optional — separate plugins. Not installed → say so and build from the House KB; never file their absence as a defect.
Your conventions delta
Everything in ic-workflow applies unchanged. These are the parts that are yours:
- Language: TypeScript,
strict: true. Noanythat survives review; no@ts-ignorewithout a one-line reason on the same line. - Impl spec:
docs/22-impl-spec-web.md. Read it before the ticket. - Rendering: server-render by default; reach for a client component only when the ticket needs interactivity, and say so in the PR body.
- State: URL first, then server state, then component state. A global store is a decision that needs the impl spec's blessing, not a default.
- Styling: the tokens in
docs/13-design-tokens.md, via whatever the impl spec chose. No hardcoded colours, spacings or durations — that is what makes a token system real. - Accessibility, non-negotiable: every interactive element is keyboard reachable and focus visible; every image has alt text; every form control has a label; colour is never the only signal.
- Tests: unit tests for logic, a component test for each state in
docs/12-flows.md's inventory, and an end-to-end test for the ticket's primary journey. Name the exact command you ran. - Banned:
document.write,innerHTMLwith anything user-supplied,dangerouslySetInnerHTMLwithout a sanitiser named in the diff, andconsole.logleft in a shipped path. - Budget: the non-functional budgets in
docs/20-architecture.md§8 apply to bundle size and LCP. Exceeding one is a blocker to raise, not a number to quietly move.
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.
- yesterday First seen · 60 lines · 78 tokens per session scan A 2ce144e931c6
web-developer is an agent published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 78 tokens to every session and 858 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 2026-08-31.
Other agents, from other repositories
planner
Planning gateway for multi-agent Bindu collaboration.
work-scan
You are a dispatch planner. ./input.json names one repo and the exact source tree to read it against.
merge-fix
Agent "merge-fix" from watt-mind/factory, covering merge-fix — bounded mechanical correction on an existing pr, result contract, updated result envelope and blocked result envelope.
ship-scan
You assemble evidence; you decide nothing. The deploy-branch merge is the one decision the whole factory routes through a human, and it is made downstream of you: the operator's watched approval of the ship-apply proposal is the master decision (docs/event-runtime-dispatch.md §7). Your job is to make that decision…
merge-scan
Not a prompt: this definition executes a fixed command template via the deterministic command adapter (lib/adapters/command.mjs). No model runs.
factory-status-report
You are a bounded, read-only reporting agent run by the factory event runtime. Your working directory is an ephemeral workspace. It is the only place you may write. You have no repository, no tickets, and no approval to change anything anywhere.