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 screenshot-to-interfacegit 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/screenshot-to-interface)<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/screenshot-to-interface"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/screenshot-to-interface/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/screenshot-to-interface"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/screenshot-to-interface.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 | $0.00029 | $0.00537 |
| Opus 5.5 | $0.00012 | $0.00215 |
| Sonnet 5.5 | $0.00006 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
screenshot-to-interface 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshot to Interface
Treat screenshots as evidence to reconstruct, not as permission to guess hidden behavior or copy unowned assets.
This skill selectively adapts MIT-licensed visual-reference concepts from Leonxlnx/taste-skill. See references/provenance.md.
Trigger boundary
Use this skill when screenshots or visual references define the primary fidelity target.
Do not trigger for greenfield art direction, generic production hardening, or asset copying without rights.
Required inputs
Resolve reference images/viewports, target stack/environment, repository state, available assets and rights, required interactions/states, acceptable fidelity tolerance, and protected user work.
Safety baseline
- Preserve uncommitted work.
- Record uncertainty where screenshots do not reveal behavior or responsive rules.
- Do not redistribute protected assets without permission.
- Keep semantic/accessibility behavior even when pixels alone do not show it.
Workflow
- Register evidence. Record each reference, viewport, state, crop, and confidence.
- Inspect implementation context. Map routes/components/styles/tokens/assets and existing behavior.
- Decompose visuals. Use
references/visual-decomposition.mdfor layout, typography, spacing, color, component, and image treatment. - Handle assets. Use
references/asset-handling.md; prefer provided/original assets and document substitutions. - Infer responsive behavior. Treat each viewport as a constraint; test intermediate widths rather than interpolating blindly.
- Choose component boundaries. Preserve semantic structure and avoid over-general abstractions built only to mimic one screenshot.
- Implement a bounded first pass.
- Compare iteratively. Use
references/fidelity-loop.mdfor side-by-side/overlay comparison and mismatch classification. - Verify interaction/accessibility. Check focus, keyboard/touch, reduced motion, text expansion, and state transitions that visual evidence alone cannot prove.
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.
- 24d ago Changed · -153 lines · -43 tokens per session ef5008293dca
- 1mo ago First seen · 205 lines · 72 tokens per session scan A e8e6db40ecd6
screenshot-to-interface is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 11d ago), licensed MIT. It adds 29 tokens to every session and 537 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
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.