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 product-design-directorgit 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/product-design-director)<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/product-design-director"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/product-design-director/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/product-design-director"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/product-design-director.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 | $0.00040 | $0.00579 |
| Opus 5.5 | $0.00016 | $0.00232 |
| Sonnet 5.5 | $0.00008 | $0.00116 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
product-design-director 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Design Director
Define a coherent product experience before implementation details harden into accidental design.
This skill selectively adapts MIT-licensed concepts from Leonxlnx/taste-skill. See references/provenance.md.
Trigger boundary
Use this skill for product UX/visual direction, redesign critique, experience principles, state/journey design, responsive behavior, and accessibility intent.
Do not trigger for literal screenshot reconstruction, routine frontend implementation, or production architecture without a design-direction question.
Required inputs
Resolve product/user goal, primary jobs/journeys, brand evidence, content/assets, existing interface when redesigning, platform/input constraints, accessibility needs, implementation constraints, and protected user work.
Safety baseline
- Preserve validated product behavior unless a change is explicitly intended.
- Distinguish evidence from aesthetic preference.
- Do not fabricate brand assets, content claims, or accessibility conformance.
- Avoid defaulting every product to one fashionable visual language.
Workflow
- Infer the design problem. Clarify audience, job, emotional/brand intent, constraints, and success signals.
- Audit before redesigning. Use
references/redesign-audit.mdto preserve working behavior and identify actual experience problems. - Set experience principles. Define hierarchy, density, feedback, trust, navigation, and content priorities.
- Calibrate direction. Use
references/direction-calibration.mdto explore distinct evidence-backed directions instead of one default aesthetic. - Model journeys/states. Cover entry, loading, empty, error, success, permission/auth, destructive/irreversible, and recovery states where relevant.
- Define the visual system. Establish typography, spacing, color roles, surfaces, imagery/icon approach, and motion purpose at the level implementation needs.
- Define responsive/accessibility behavior. Use
references/accessibility-and-responsive-review.md; specify transformations, not just desktop/mobile snapshots. - Critique and hand off. Compare the proposed system against the brief and make implementation-critical decisions explicit.
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 Changed · -164 lines · -39 tokens per session 6bc4fb37b8a8
- 1mo ago First seen · 215 lines · 79 tokens per session scan A 5e11756f4855
product-design-director is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 16d ago), licensed MIT. It adds 40 tokens to every session and 579 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
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.
hunt
Finds root cause of errors, crashes, unexpected behavior, and failing tests before applying any fix. Not for code review or new features.
check
Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.
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.