Borrowing it
Nothing to install: this file belongs to zhu-kai/whodecided. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zhu-kai/whodecided/main/.claude/skills/workbench-ui/SKILL.mdgit clone --depth 1 https://github.com/zhu-kai/whodecidedWrote 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/zhu-kai/whodecided/workbench-ui)<a href="https://agentmods.dev/skills/zhu-kai/whodecided/workbench-ui"><img src="https://agentmods.dev/badge/skills/zhu-kai/whodecided/workbench-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/zhu-kai/whodecided/workbench-ui"><img src="https://agentmods.dev/badge/skills/zhu-kai/whodecided/workbench-ui.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 | $0.00040 | $0.00364 |
| Opus 5.5 | $0.00016 | $0.00146 |
| Sonnet 5.5 | $0.00008 | $0.00073 |
| Haiku 4.5 | $0.00004 | $0.00036 |
Grade A, and why
workbench-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 1mo 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
The workbench is ONE template-literal string emitting a self-contained page (embedded JSON, vanilla JS, no CDN).
Escaping trap (breaks the page silently): inside the emitted <script>, every backslash needs doubling for the outer literal - \\n not \n, \\" not \", and regex character classes like /[/]/ instead of escaped slashes. A single unescaped backslash produces a blank page with a console error.
Conventions:
- All user-visible strings live in the
Tobject, English only. - One signal, one cue: risk is the red left edge (high only), category is the small colored label, relationships are chips under the text. Never stack a second cue for the same fact.
- Negative/actionable info goes in the drawer's needs-attention block; healthy states fold into collapsed
<details class="dsec">sections. - Benign categories render muted; only silent (red) should pull the eye.
Verify (required before done):
npm run build && npm test.- Render real data - a repo with a populated
.wdd/(not synthetic fixtures), viawdd review --htmlor a small node script importingdist/render/html.js. - Serve over http (file:// is blocked for MCP browsers), open with Playwright: assert zero console errors, click through a decision drawer, screenshot and actually look at it.
- Clean up: temp server, screenshots, scratch scripts.
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.
- 1mo ago First seen · 21 lines · 40 tokens per session scan A 2b034096e1f1
workbench-ui is a skill published in the GitHub repository zhu-kai/whodecided (22 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 364 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.
glycoengineering
Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). For glycoprotein engineering, therapeutic antibody optimization, and vaccine design.
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…
pysam
Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.
openalex-database
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly…