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 vmobifystudio/app-dev-team --skill localisationgit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWrote 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/vmobifystudio/app-dev-team/localisation)<a href="https://agentmods.dev/skills/vmobifystudio/app-dev-team/localisation"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/localisation/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/vmobifystudio/app-dev-team/localisation"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/localisation.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 | $0.00074 | $0.00578 |
| Opus 5.5 | $0.00030 | $0.00231 |
| Sonnet 5.5 | $0.00015 | $0.00116 |
| Haiku 4.5 | $0.00007 | $0.00058 |
Grade A, and why
localisation 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Localisation
Localisation is an architecture decision taken at the first string, and a translation task only at the end. Teams that reverse the order pay for it twice.
Where a platform skill exists, use it: axiom-localization on Apple platforms. External and
optional — missing → follow this file, never file its absence as a defect.
Do this from the first ticket, in every locale count including one
- Every user-visible string is a key in the catalogue. No string literal in a view, ever. This is cheap now and a full re-read of the codebase later.
- Never concatenate a sentence from fragments. Word order differs by language. Use one parameterised string per sentence.
- Plurals use the platform's plural rules, not
if count == 1. Several languages have more than two plural forms and1 itemsis the cheapest possible way to look unfinished. - Dates, times, numbers, currencies and units go through the locale-aware formatter. A hand-formatted date is wrong in most of the world, silently.
- Never sort or compare user-facing text with byte comparison. Use the locale-aware collator.
Layout
- Assume text grows 30–40% from English. A button that fits exactly is a button that clips.
- RTL is a layout mode, not a translation. Use leading/trailing, never left/right; mirror directional icons (back, next, progress) and never mirror ones with real-world orientation (a clock, a logo, a play button).
- Test at the longest supported locale and the largest Dynamic Type together — that combination is where clipping actually happens.
Region is not language
Region determines: currency and price tier, legal and privacy obligation (privacy-reviewer),
store metadata and rating, available payment methods, and sometimes whether a feature may ship at
all. A locale added to the catalogue is a market entered. Say so explicitly rather than letting
a translation file imply it.
Output
The locale set and its consequences are stated in docs/12-flows.md (navigation and layout impact)
and in docs/15-aso.md (store metadata per locale). Pseudo-localise before you have translations —
it finds hardcoded strings and clipping without waiting for a translator.
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 · 47 lines · 74 tokens per session scan A 1837077323c3
localisation is a skill published in the GitHub repository vmobifystudio/app-dev-team (5 stars, last pushed 12d ago), licensed MIT. It adds 74 tokens to every session and 578 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
execute-task
Implement one task (or a cohesion bundle) from a signed-off spec (Ready or Active): recompute the execution freshness gate, write the verifying test first, implement to green, run the project's full CI with adaptive retry, converge via the stepsconvergence list (default /polish --nested), then open a draft PR…
orchestrate
Advance one planwright spec by one step: pick the next ready unit critical-path-first (or a cohesion bundle), run the freshness gate, record the dispatch under the per-spec lock, and dispatch /execute-task via the backend. A stateless, disposable orchestrator session; a reconcile sweep rebuilds from disk. Never…
spec-kickoff
Walk a spec bundle section by section to mutual understanding, producing the signed-off kickoff brief downstream skills execute from. On sign-off: runs the Discovery-Rigor lens pass, flips Draft to Ready, records the sign-off record (anchor last), commits, pushes, opens a draft PR, then on clean completion marks the…
tower
The front door: a standing conversational session that takes any ask about the repository in plain language, answers questions, and routes work that changes the repository per request onto visual flight (an isolated worker that lands a draft PR) or instrument flight (the spec pipeline), stating its grounds, with…
polish
Autonomous act-then-review convergence loop: iterate /self-review passes, draining every action disposition (Auto-applicable and Agent-resolvable applied, Needs-sign-off applied on the branch) until only irreducible Needs-human-judgment forks remain, then hand off. Local-only: never pushes, never creates a PR. Pass…
ramp
Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.