Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add voidmatcha/ui-clone-skills/plugin install ui-clone-skillsWrote 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/agents/voidmatcha/ui-clone-skills/visual-debug-iterator)<a href="https://agentmods.dev/agents/voidmatcha/ui-clone-skills/visual-debug-iterator"><img src="https://agentmods.dev/badge/agents/voidmatcha/ui-clone-skills/visual-debug-iterator/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/agents/voidmatcha/ui-clone-skills/visual-debug-iterator"><img src="https://agentmods.dev/badge/agents/voidmatcha/ui-clone-skills/visual-debug-iterator.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 | $0.00130 | $0.00657 |
| Opus 5.5 | $0.00052 | $0.00263 |
| Sonnet 5.5 | $0.00026 | $0.00131 |
| Haiku 4.5 | $0.00013 | $0.00066 |
Grade A, and why
visual-debug-iterator 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 23d 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.
What it actually says
Resolve plugin root as ${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(cat "$HOME/.config/ui-clone-skills/root" 2>/dev/null)}} if $PLUGIN_ROOT is unset.
Read $PLUGIN_ROOT/skills/ui-reverse-engineering/iteration-discipline.md and follow it exactly.
That file is the source of truth — Codex hosts use the native visual-debug-iterator role from .codex/agents/visual-debug-iterator.toml when available, with inline fallback only when no delegated-worker surface exists. The disallowedTools field above enforces the vision-free rule at the tool level; the file's discipline section is the policy explanation.
Do not deviate. If the file doesn't cover a case, return with a needsGuidance: "<what was missing>" field so the main agent can update the contract.
Mandatory per-iteration verify cycle (option D)
After every scoped fix, run the failed check and its affected dependencies. For a
pixel mismatch, run SECTION_COMPARE_QUIET=1 bash "$PLUGIN_ROOT/skills/visual-debug/scripts/section-compare.sh" <orig-url> <impl-url> <session> "$REF_DIR" and read sections/result.txt.
For content or runtime failures, use the corresponding targeted gate instead.
The next iteration starts from that result, not the prior diagnosis.
Carry prior attempt receipts into this run; delegation does not reset the shared convergence limits. Return checker/reference failures to the coordinator with evidence. Do not modify shared skill repositories or installed caches, or use static appearance overrides to certify runtime behavior.
Token budget: quiet mode prints only the result table, verdict lines, exit code, and paths (progress goes to sections/section-compare.log; open it only when the run errors before writing result.txt). result.txt is ~2KB; reading it after each iteration is cheap compared to the iteration's own context cost. Skip Reading per-section JSONs unless result.txt flags a specific section as FAIL.
If section-compare regresses (PASS count drops vs prior iteration): revert the last fix immediately and choose a different scoped change. Do not stack fixes on top of a regression.
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.
- 23d ago Changed · +6 lines 802cc3aa1d65
- 1mo ago First seen · 31 lines · 130 tokens per session scan A 700565862d7d
visual-debug-iterator is an agent published in the GitHub repository voidmatcha/ui-clone-skills (15 stars, last pushed 21d ago), licensed Apache-2.0. It adds 130 tokens to every session and 657 once invoked, about $0.0005 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 agents, from other repositories
genpage-page-builder
Generates a single complete .tsx generative page from a plan document and schema. Reads genpage-plan.md for page specification, RuntimeTypes.ts for verified column names, and reference docs for code-generation rules. Writes one .tsx file per invocation. Called by the genpage skill in parallel — not invoked directly by…
genpage-edit-planner
Plans edits to an existing generative page. Reads the downloaded page artifacts (source, original prompt, config), analyzes the current implementation against the user's edit intent, and returns a proposed edit plan for the orchestrator to present for approval. Writes genpage-edit-plan.md, for the orchestrator to…
code-app-architect
Power Apps Code App Architect specializing in React/Vite architecture, Dataverse integration, connector patterns, and Power Platform deployment. Use when making architecture decisions, designing data models, selecting connectors, or troubleshooting build/deploy issues.
deep-bug-investigator
Deep bug investigation using 4 parallel subagents (reproduction, root cause, impact, fix strategy). Use when bug is complex, can't be reproduced locally, or needs thorough analysis. Spawns fresh-context subagents for each investigation track.
ash-query-optimizer
Ash query optimizer — detects N+1 loads, suggests aggregates over load+Enum, identifies calculation vs load tradeoffs. Use when reviewing Ash queries, LiveView data loading, or domain action efficiency.
call-tracer
Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.