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 skills/cmdr-chara/codex-toolkit/production-web-buildernpx skills add cmdr-chara/codex-toolkit --skill production-web-buildergit clone --depth 1 https://github.com/cmdr-chara/codex-toolkitWrote 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/cmdr-chara/codex-toolkit/production-web-builder)<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/production-web-builder"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/production-web-builder.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.02305 |
| Opus 5 | $0.00041 | $0.01153 |
| Sonnet 5 | $0.00016 | $0.00461 |
| Haiku 4.5 | $0.00008 | $0.00231 |
Grade A, and why
production-web-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 4d 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Production Web Builder
Build the smallest coherent web system that satisfies product behavior and production constraints. Prefer platform/framework capabilities until a demonstrated requirement justifies a dependency.
Trigger boundary
Use this skill for:
- implementing a production web feature, route, application, or redesign handoff;
- auditing an existing web interface for architecture and production readiness;
- choosing rendering/data/form/state/motion/testing approaches from repository evidence;
- completing browser, accessibility, performance, SEO, observability, and deployment verification.
Do not trigger for:
- defining the product's visual direction—use
product-design-director; - reference reconstruction where fidelity is the primary problem—start with
screenshot-to-interface; - choosing or implementing Flutter/Expo/mobile-native applications;
- adding a package because it appears on a preferred stack list.
Required inputs
Capture:
- repository state, framework/runtime/package manager, deployment target, and supported browsers;
- product/design requirements, flows, content, responsive and accessibility acceptance criteria;
- data, API, authentication/authorization, cache, mutation, and error contracts;
- SEO/discovery needs, localization, privacy/security, analytics, and observability policy;
- performance budget or critical user journeys;
- test/CI/deploy tooling and environments.
Run the read-only inventory to locate current choices before recommending new ones:
python skills/production-web-builder/scripts/web_project_inventory.py . --format markdown
Safety baseline
- Inspect and preserve uncommitted work; avoid broad formatting or generated churn.
- Read manifests, lockfile, framework configuration, and existing patterns before package changes.
- Do not expose secrets in client bundles, logs, source maps, browser storage, or test fixtures.
- Treat server/client and trusted/untrusted boundaries explicitly; client validation is not authorization.
- Do not disable type, lint, accessibility, CSP, certificate, auth, or browser safeguards to make a check pass.
- Confirm package commands and compatibility from current official sources and the active repository; never invent CLI flags.
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.
- 4d ago First seen · 223 lines · 81 tokens per session scan A 4689387dbe16
production-web-builder is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 6d ago), licensed MIT. It adds 81 tokens to every session and 2,305 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 skills, from other repositories
boss-advanced
Advanced Boss orchestration patterns — Agent Teams leadership, 6-section delegation template, Skill vs Agent conflict resolution, Guardian pattern, and AI-slop detection.
gstack-sprint
3-Phase Sprint workflow — design → execute → review with user interaction at decision points.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
briefing-vault
Initialize, manage, and search the per-project .briefing/ vault. Obsidian-compatible persistent knowledge base.
manage-skills
세션 변경사항을 분석하여 검증 스킬 누락을 탐지합니다. 기존 스킬을 동적으로 탐색하고, 새 스킬을 생성하거나 기존 스킬을 업데이트한 뒤 CLAUDE.md를 관리합니다.
release
Bump package.json version and create a git tag for npm release. Accepts semver bump type (patch/minor/major) or explicit version.