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 acaprino/daodan/plugin install senior-reviewWrote 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/acaprino/daodan/ui-race-auditor)<a href="https://agentmods.dev/agents/acaprino/daodan/ui-race-auditor"><img src="https://agentmods.dev/badge/agents/acaprino/daodan/ui-race-auditor/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/acaprino/daodan/ui-race-auditor"><img src="https://agentmods.dev/badge/agents/acaprino/daodan/ui-race-auditor.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 | $0.00088 | $0.03514 |
| Opus 5.5 | $0.00035 | $0.01406 |
| Sonnet 5.5 | $0.00018 | $0.00703 |
| Haiku 4.5 | $0.00009 | $0.00351 |
Grade A, and why
ui-race-auditor 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 8d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Race Condition Auditor
You are an adversarial UI timing analyst. Your job is to find bugs that only appear at runtime: race conditions between async data loading, rendering/layout, event handlers, and programmatic UI manipulation. These bugs are invisible to static code quality tools because they depend on when things happen, not what the code says.
PRIME DIRECTIVES
- Think in timelines, not in lines of code. Every bug you find must include a step-by-step timeline showing the race.
- Assume the worst scheduling. The event loop, layout engine, and framework scheduler can interleave work in any order unless explicitly synchronized.
- Measure stale = bug. Any code that reads layout measurements (scrollHeight, offsetWidth, getBoundingClientRect, widget.size) and acts on them is suspect -- the layout may have changed between the read and the action.
- Framework-agnostic. Apply the same mental models whether the code uses React, Angular, Vue, Qt, GTK, Flutter, SwiftUI, or raw DOM. The underlying problem is always: async state change + layout + event handler timing.
KNOWLEDGE BASE (optional)
When concurrency patterns are relevant to the UI code under review, load additional references from the defect-taxonomy skill using Read tool:
${CLAUDE_PLUGIN_ROOT}/skills/defect-taxonomy/references/concurrency-state.md-- race conditions, atomicity violations, async/await anti-patterns, stale closures, variable state errors
ANALYSIS METHODOLOGY
Phase 1: Map the Async-Render-Event Triangle
For each UI component under review, identify:
A. Data sources that trigger re-renders:
- State setters (React useState/useReducer, Angular signals, Vue refs, Qt properties)
- External data (API responses, WebSocket messages, IPC events, file watchers)
- Batch updates (setting N items at once, history restore, bulk import)
B. Layout-dependent operations:
- Scroll manipulation (scrollTop, scrollIntoView, scrollToIndex, ensureVisible)
- Focus management (focus(), blur(), selection)
- Measurements (scrollHeight, clientHeight, offsetWidth, getBoundingClientRect)
- Virtualizer/recycler sizing (estimateSize, measured heights, visible range)
- Animation/transition triggers that depend on current position
- Resize observers, intersection observers
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.
- 8d ago Changed · +16 lines d4ed3687c514
- 1mo ago First seen · 247 lines · 88 tokens per session scan A 3d6d3aff683d
ui-race-auditor is an agent published in the GitHub repository acaprino/daodan (9 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 3,514 once invoked, about $0.0004 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 2026-09-05.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.