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 chan4lk/specclaw --skill bf-uigit clone --depth 1 https://github.com/chan4lk/specclawWrote 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/chan4lk/specclaw/bf-ui)<a href="https://agentmods.dev/skills/chan4lk/specclaw/bf-ui"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/bf-ui/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/chan4lk/specclaw/bf-ui"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/bf-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00015 | $0.03447 |
| Opus 5.5 | $0.00006 | $0.01379 |
| Sonnet 5.5 | $0.00003 | $0.00689 |
| Haiku 4.5 | $0.00002 | $0.00345 |
Grade A, and why
bf-ui 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 15d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specclaw bf-ui
First, run specclaw-ensure-init .specclaw — idempotently creates .specclaw/ if it doesn't exist (silent if already initialized; auto-inits using the current directory's basename as the project name).
Extract, capture, and review the UI-fidelity dimension of a rebuild. Read-only side-command — no specclaw-validate-change call, no <change> gate, matching the analyze/architecture/domain/clarify/baseline/rebuild-plan pattern.
This command is optional and never required. The whole brownfield pipeline works without it. /specclaw-bf:bf-clarify asks the UI fidelity policy question (SQ-013) whether or not this command was ever run, and /specclaw-bf:bf-rebuild-plan only requires UI grounding when that policy is decided FAITHFUL or THEME-ONLY. A project on REINTERPRET answers one question and is done.
UI is never a golden-master seam. templates/seams.md's ## Excluded: UI Automation class stands unchanged, and /specclaw-bf:bf-replay is untouched by this command except for one informational footer line. Nothing this command produces is replayable, diffable, or a proof of pixel-identity — visual fidelity is established by a human reviewing recorded evidence (Mode C's ui-review.md), and this command must never be described as doing more than that.
Determine the mode from the user's message:
| If the message contains | Mode |
|---|---|
--record |
Mode B — record the human's captures |
--checklist <change-name> |
Mode C — generate the review table (run in the NEW repo) |
| neither | Mode A — design/extract (default) |
Mode A — design / extract (default: no flag)
Run this in the legacy repo, after /specclaw-bf:bf-domain (its domain-model.md and functional-spec.md are what the widget cross-reference keys against) and before /specclaw-bf:bf-clarify (so any pending question this run raises is ingested in the same clarify sweep).
- Collect:
mkdir -p .specclaw/analysis/.collect specclaw-bf-ui collect .specclaw [path] > .specclaw/analysis/.collect/ui-extract.json[path]defaults to the repository root when omitted. This parses the priorui-inventory.md/design-tokens.jsonfor their permanentSCR-###/TK-###assignments before archiving all three prior Mode A outputs into.specclaw/ui/archive/, then emits one JSON object: resolved paths, those prior id assignments, the next free ids, which analysis documents are present, the legacy repo's HEAD sha, and a stack-agnostic extension histogram of every file in scope. Check the exit status before spawning. If it exits non-zero, surface its stderr message to the user verbatim and stop — don't retry, don't guess a different path, and never hand the agent a path to a half-written file.
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.
- 15d ago Changed · +15 tokens per session 26ca365a70ab
- 1mo ago Changed · +2 lines 21967b4fcd0a
- 1mo ago First seen · 120 lines · 0 tokens per session scan A 99e140c0be33
bf-ui is a skill published in the GitHub repository chan4lk/specclaw (13 stars, last pushed 8d ago), licensed MIT. It adds 15 tokens to every session and 3,447 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 skills, from other repositories
ui-designer
Aura - Senior UI/UX Design Architect with 12+ years creating premium digital experiences. Use when designing landing pages, dashboards, mobile apps, design systems, component libraries, or brand-aligned UI. Specializes in React/Tailwind/Framer Motion prototypes, responsive design, micro-interactions, and…
from-intake
A workflow for reviewing material brought from another workspace and carrying relevant brand evidence into the project's assets. It checks inventories, brand guides, logos, and image sources before anything is used.
build-screen
A workflow for implementing one specified app screen with Toss Design System components and adding it to the app's route list. It also requires empty, loading, and failure states, with a way to retry after failure.
ux-researcher
UX Researcher (/ux) — the research side of UX: user interviews, surveys, usability testing, personas, journey maps, information architecture, card sorting, jobs-to-be-done, and turning findings into prioritized design requirements. Use when you need to understand users, validate a concept, define IA/navigation, plan…
prototype
Answer one open question from a requirement brief with a throwaway prototype (原型) — logic, UI, or a feature slice — then record the answer, the evidence, and the prototype's commit in the brief and remove the prototype in the next commit. Use when a brief's Open Questions entry is marked needs prototype, or the user…
options
Present multiple design options as a vertical stack of anchored turns.