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 sigistry/marketplace --skill catalog-hygienegit clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/sigistry/marketplace/catalog-hygiene)<a href="https://agentmods.dev/skills/sigistry/marketplace/catalog-hygiene"><img src="https://agentmods.dev/badge/skills/sigistry/marketplace/catalog-hygiene/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/sigistry/marketplace/catalog-hygiene"><img src="https://agentmods.dev/badge/skills/sigistry/marketplace/catalog-hygiene.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 | $0.00093 | $0.00790 |
| Opus 5 | $0.00046 | $0.00395 |
| Sonnet 5 | $0.00019 | $0.00158 |
| Haiku 4.5 | $0.00009 | $0.00079 |
Grade A, and why
catalog-hygiene 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 11d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Catalog Hygiene
Purpose
Provide a standardized, static methodology for keeping translation catalogs correct and complete, and for making a UI ready for right-to-left languages. A catalog rots the moment code and translations drift: keys used in code but missing from a locale render raw ids to users, keys left in the catalog after a feature is deleted are paid-for cruft, and values that were copy-pasted from English look translated but ship the wrong language. RTL readiness is the other half, a layout full of physical left/right CSS silently breaks in Arabic and Hebrew.
Catalog Health Checks
Cross-reference the code's translation calls against every locale file and report:
| Check | Definition | Impact |
|---|---|---|
| Missing key | used in code, absent in a locale | fallback text or a raw key shown to users |
| Unused key | in the catalog, referenced nowhere | dead weight; wasted translation spend |
| Untranslated value | target value byte-equal to the source | looks done, ships the source language |
| Placeholder drift | {name}/{count} set differs across locales |
undefined in the string or a formatter throw |
| ICU error | malformed plural/select, unbalanced braces |
renders literally or throws at runtime |
| Missing plural category | locale lacks a CLDR form its grammar needs | wrong number agreement for real inputs |
Measure coverage per locale = translated keys ÷ source keys, and treat the source locale (usually en) as the reference set.
Key Design Principles
- Namespace keys by feature/component and derive them from meaning, not the English string, so re-wording copy does not churn keys.
- One key = one message = one place. Reuse before duplicating; do not fork
save/save_button/btn_savefor the same word. - Never machine-translate to fill a gap, leave the value empty (or the framework's missing sentinel) for a human translator.
RTL Readiness In One Line
Replace direction-baked physical CSS with logical properties (margin-left → margin-inline-start, left → inset-inline-start, text-align: left → start). Logical properties resolve to the correct physical side based on the element's dir, so one stylesheet serves both directions. What logical properties cannot fix, mirrored icons, x-axis transforms, directional shadows, and bidi text, needs human judgment. See references/rtl-logical-properties.md.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 40 lines · 93 tokens per session scan A b432711c0d5e
catalog-hygiene is a skill published in the GitHub repository sigistry/marketplace (3 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 790 once invoked, about $0.0005 per session on Opus 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 skills, from other repositories
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…
create-app
Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way…
37signals-way
Build lean, opinionated products using the 37signals philosophy from "Getting Real", "Rework", and "Shape Up". Use when the user mentions "Getting Real", "Rework", "Shape Up", "37signals", "Basecamp method", "six-week cycles", "fixed time variable scope", "appetite vs estimates", "betting table", "breadboarding", "fat…
clean-architecture
Structure software around the Dependency Rule: source code dependencies point inward from frameworks to use cases to entities. Use when the user mentions "architecture layers", "dependency rule", "ports and adapters (hexagonal)", "onion architecture", "screaming architecture", "where should business logic go"…
cold-start-problem
Start and scale networked products using Andrew Chen's "The Cold Start Problem" framework for network effects. Use when the user mentions "network effects", "chicken and egg", "cold start", "two-sided marketplace", "atomic network", "hard side", "liquidity", "critical mass", "invite-only launch", "how do I get my…