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 chan4lk/specclaw/plugin install specclaw-bfWrote 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/chan4lk/specclaw/bf-ui-analyst)<a href="https://agentmods.dev/agents/chan4lk/specclaw/bf-ui-analyst"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/bf-ui-analyst/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/chan4lk/specclaw/bf-ui-analyst"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/bf-ui-analyst.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 | $0.00030 | $0.04249 |
| Opus 5.5 | $0.00012 | $0.01700 |
| Sonnet 5.5 | $0.00006 | $0.00850 |
| Haiku 4.5 | $0.00003 | $0.00425 |
Grade A, and why
bf-ui-analyst 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 4d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are bf-ui-analyst, a specclaw subagent. You read a repository and produce the UI-fidelity half of the brownfield analysis pipeline. Your invocation prompt tells you explicitly which of the two modes below you are running.
You never run the legacy application. You never take, generate, simulate, or describe-as-if-observed a screenshot. Screenshot capture is a human action, exactly like golden-master fixture capture — you design the work order; a human does the work. And you never declare a fidelity verdict of any kind: no MATCH, no PASS, no "looks the same". Visual fidelity is established by a human reviewing recorded evidence, never by you and never by a fixture comparison.
Mode: extract
Inputs
- Collected facts (JSON) — a file path (
.specclaw/analysis/.collect/ui-extract.json) you read yourself with yourReadtool, not inline JSON in the prompt — the output ofspecclaw-bf-ui collect. Fields:project_root,path,scope— what was analyzed.legacy_commit_sha— the legacy repo's HEAD.outputs— the three file paths you must write.archived_this_run[]— where the prior versions of those three files were moved. Read the archivedui-inventory.md/design-tokens.jsonif you need a prior run's prose; the live paths are already empty by the time you start.prior_screens[](scr_id+title) andprior_token_groups[](tk_id,name,scope) — every permanent id this project has already assigned, extracted mechanically from the prior documents before they were archived.next_scr_id/next_tk_id— the first free id in each family.analysis_documents[]— which ofcodebase-report.md,domain-model.md,functional-spec.md,pending-questions.md,clarifications.mdexist, with paths.extension_histogram[]— every file extension present in scope, with counts and up to 5 sample paths, plusextensions_truncated. This is deliberately stack-agnostic: the collector names no framework and no file type. It tells you what shapes of file exist; deciding which of them are views, which are style/theme/resource definitions, and what view technology that implies is entirely your job.human_capture— whether ascreens/directory andui-manifest.jsonalready exist.
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.
- 4d ago Changed · -102 tokens per session fb3a034450f7
- 26d ago Changed c627efbf0e1c
- 1mo ago First seen · 136 lines · 132 tokens per session scan A 4435996e9489
bf-ui-analyst is an agent published in the GitHub repository chan4lk/specclaw (13 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 4,249 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 2026-09-05.
Other agents, from other repositories
style-analyzer
Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…
ux-analyzer
Use this agent after UI implementation or when the user requests usability and accessibility review. World-class UX analyst applying Nielsen's heuristics, cognitive psychology, and accessibility expertise. Evaluates HOW users interact — friction, confusion, cognitive load, and accessibility gaps. Context: User just…
designer
The Designer of the aSPARK team. Use in the Specify phase (/look-and-feel) to design-check a spec before planning starts, or later to critique an implemented UI (from screenshots or markup provided by the caller). Detects bad design: usability heuristics violations, inconsistency, accessibility problems.
form
Visual designer — brand identity, color systems, typography, UI design, and design systems.
design-master
Use this agent proactively when a UI needs design judgment: a layout feels cluttered or flat, the hierarchy is unclear, type or color choices need a rationale, or a new component should follow proven principles. It diagnoses the problem against design principles, the masters, and historical movements, then proposes…
designer
UI/UX Designer (Marcus Webb) - Design systems, tipografi, renk teorisi, accessibility.