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 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/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/cmdr-chara/codex-toolkit/production-web-builder"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/production-web-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 | $0.00037 | $0.00712 |
| Opus 5.5 | $0.00015 | $0.00285 |
| Sonnet 5.5 | $0.00007 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
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 24d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Production Web Builder
Build web behavior around repository constraints, trust boundaries, and user journeys rather than a default dependency stack.
Trigger boundary
Use this skill for production web implementation or audits covering rendering, components, data, forms, auth boundaries, responsive behavior, accessibility, performance, SEO, observability, or browser integration.
Do not trigger for visual direction alone, literal screenshot reconstruction alone, mobile-platform selection, or a version migration whose central decision is compatibility.
Required inputs
Resolve repository/working-tree state, framework/runtime, routes and rendering model, product flows/states, data/auth contracts, supported browsers/devices, deployment adapter, existing tests, and protected user work.
When useful, run the read-only inventory:
python skills/production-web-builder/scripts/web_project_inventory.py . --format markdown
Verify its signals manually.
Safety baseline
- Preserve uncommitted work and existing repository conventions.
- Do not start with a package list.
- Prefer built-in platform/framework capabilities or existing repository packages when sufficient.
- For new dependencies, verify compatibility, maintenance, license, security/deprecation, runtime/bundle cost, and removal path.
- Client validation is not authorization; keep secrets and privileged enforcement server-side.
Workflow
- Map execution and trust. Identify server/edge/client/build-time ownership, caching, authentication/authorization, assets, CSP/security headers, and deployment limits.
- Model behavior first. Define initial/loading/empty/error/retry/offline/stale/unauthorized states, mutation semantics, navigation, focus, and recovery.
- Choose architecture conditionally. Read
references/package-selection.mdand the dated ecosystem reference only when a dependency/framework decision is material. - Implement semantic boundaries. Prefer native semantics and explicit component/data ownership. Keep invalid state combinations unrepresentable where practical.
- Implement data/forms safely. Validate untrusted input at the server boundary, authorize protected operations, define cache/invalidation ownership, preserve recoverable form input, and control duplicate effects.
- Apply responsive/a11y behavior. Test intermediate widths, zoom, long/localized content, input modes, reduced motion, focus, and semantic interaction.
- Measure web performance when material. Read
references/core-web-vitals.mdfor field-first LCP/INP/CLS work; use measured evidence rather than Lighthouse-score chasing. - Verify production behavior. Use
references/production-readiness.mdfor browser journeys, failure paths, observability, build/preview behavior, SEO where relevant, and rollback/flag controls.
What ships with it
6 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.
- 24d ago Changed · -165 lines · -44 tokens per session 2837f71e466f
- 1mo 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 11d ago), licensed MIT. It adds 37 tokens to every session and 712 once invoked, about $0.0001 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
trace
Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
code-coherence-review
Reviews code and plans for logic coherence, correctness, and structural integrity.