agentmods.dev

SidewalkWebpage: Skill for Claude Code

.claude/skills/onboard-city/SKILL.md

onboard-city is a skill for Claude Code from ProjectSidewalk/SidewalkWebpage. It costs 70 tokens per session (3,724 once invoked), scanned A, original, MIT.

A guided workflow for adding a new city to Project Sidewalk, including data collection, map-data building, imagery checks, translations, configuration, and server handoff. Project Sidewalk is a mapping project that uses street-level data to support accessibility work.

In plain words
What is it for?
Use it to prepare a city's source data, run geographic-information-system (GIS) quality checks, preflight imagery providers, apply translations, configure the city, and hand the result to the server.
Why use it?
It brings the many checks and setup steps into one runbook while leaving judgment calls to the agent. It also warns about where the commands must be run and where generated onboarding files are stored.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is ProjectSidewalk/SidewalkWebpage's own configuration. It tells Claude Code how to work on SidewalkWebpage itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything SidewalkWebpage configures →

not rated 111repo +1 changed 1mo ago A scan 70 tokens original MIT
View source ↗ ProjectSidewalk/SidewalkWebpage projectsidewalk.org
Reuse

Borrowing it

Nothing to install: this file belongs to ProjectSidewalk/SidewalkWebpage. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ProjectSidewalk/SidewalkWebpage/develop/.claude/skills/onboard-city/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ProjectSidewalk/SidewalkWebpage

Made for: Claude Code.

Wrote 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.

agentmods badge for onboard-city

README.md
[![agentmods](https://agentmods.dev/badge/skills/projectsidewalk/sidewalkwebpage/onboard-city/github.svg)](https://agentmods.dev/skills/projectsidewalk/sidewalkwebpage/onboard-city)
Your own site
<a href="https://agentmods.dev/skills/projectsidewalk/sidewalkwebpage/onboard-city"><img src="https://agentmods.dev/badge/skills/projectsidewalk/sidewalkwebpage/onboard-city/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.

agentmods 80×15 button for onboard-city

Your own site · 80×15
<a href="https://agentmods.dev/skills/projectsidewalk/sidewalkwebpage/onboard-city"><img src="https://agentmods.dev/badge/skills/projectsidewalk/sidewalkwebpage/onboard-city.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,724 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.03724
Opus 5.5 $0.00028 $0.01490
Sonnet 5.5 $0.00014 $0.00745
Haiku 4.5 $0.00007 $0.00372

Measured 1mo ago against content hash 3c3d2a47bfb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

onboard-city 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.

.claude/skills/onboard-city/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Onboard a city

Two commands and this skill. Read docs/onboarding-a-city.md once; it is the runbook this skill drives.

make build-city-data id=<city-id> args="..."   # tools/city/onboard_city.py → db/onboarding/<city-id>/ (QA gpkg, SQL, report, endpoints csv)
make check-imagery   id=<city-id> args="--sample --<provider>"   # preflight, one row per provider in preflight_report.md
make onboard-city    id=<city-id>              # tools/city/setup_new_city.py → configs, GA, schema, fill, scan, gradient, dump + handoff

Everything under db/onboarding/ is git-ignored. The db container sees it at /opt/onboarding/ only from the main checkout (db/ is the bind mount), so run these from the main checkout, not a worktree.

1. Intake — ask before building

  • City id. Lowercase kebab-case ending in the state for US cities (laurens-ia), the country elsewhere (bayonne-fr). It becomes SIDEWALK_CITY_ID, the schema (sidewalk_laurens_ia), and the output dir.
  • Server name. The id without its suffix (sidewalk-laurens), unless a clearly larger city shares the name (sidewalk-newport-ky).
  • Imagery provider. gsv unless the partner says otherwise; mapillary / panoramax / infra3d need the matching credentials in the web container (Panoramax needs none). If unsure, the preflight in step 3 decides.
  • Neighborhood boundaries, in this order of preference, and record where they came from (--regions-source, a URL or the collaborator's email — it lands in region.data_source):
    1. A partner- or city-supplied dataset (any OGR format/CRS; note its name column for --region-name-col).
    2. The city's open-data portal (ArcGIS Hub / Socrata / CKAN / data.gouv.fr …): search "neighborhoods", "quartiers", "barrios", "council districts". Prefer official, non-overlapping polygons that tile the city.
    3. Let the tool fall back: OSM neighbourhood polygons (used only above 75% coverage), then US census tracts (TIGERweb), then the whole city as one region (small towns; split later in QGIS if it grows).
  • A one-region city takes the city's name (from --place), not the source's — otherwise a small town is the neighbourhood "Census Tract 7801" in every mission message and API response. Use --single-region-name with a --boundary-file, or to override. Names you chose (--regions-file, --rename-regions, a --merge-regions target) are left alone.
  • City boundary. --place "<City, State, Country>" geocodes the OSM admin boundary; check the report's "Boundary:" line names the right place. A partner file goes in with --boundary-file.
  • Scope. Whole city, or a phased launch opening some regions first (onboard-city asks; the imagery scan covers everything either way).

Read the full file on GitHub · 186 lines

Changes

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.

  1. 1mo ago Changed · +1 lines 3c3d2a47bfb1
  2. 1mo ago Changed · +5 lines cb04312b243f
  3. 1mo ago Changed · +1 lines e1725851894f
  4. 1mo ago Changed · +39 lines 56761c0b6908
  5. 1mo ago Changed · +22 lines 968ae7a3b43b
  6. 1mo ago Changed · +1 lines a82be89331e2
  7. 1mo ago Changed · +3 lines 04b6fa859a52
  8. 1mo ago First seen · 114 lines · 70 tokens per session scan A 15899b428b02

Subscribe to this mod's changes

onboard-city is a skill published in the GitHub repository ProjectSidewalk/SidewalkWebpage (111 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 3,724 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 2026-09-07.

Project managementaccessibilitygoogle-streetviewmapillaryopenstreetmaposmsidewalk
Related

Other skills, from other repositories

implement-github-feature

Design and implement a new feature or component from a GitHub issue. Use for net-new functionality, not bug fixes.

AgnosticUI/agnosticui · 29 tokens

contributions-hub

GitHub community: discussions, moderation, contributor health, CLAs.

Community-Access/accessibility-agents · 19 tokens

issue-tracker

GitHub issues: find, triage, review and respond, with written reports.

Community-Access/accessibility-agents · 21 tokens

team-manager

GitHub org teams: create, staff, onboard, offboard and audit access.

Community-Access/accessibility-agents · 20 tokens

fix-github-issue

Fix a GitHub issue by number. Use when asked to fix GitHub issues.

AgnosticUI/agnosticui · 23 tokens

kb-open-source-accessibility-framework

Reference data, not a reviewer. Open Source Accessibility Framework: phases, action IDs and cadence, tracking issue, framing.

Community-Access/accessibility-agents · 31 tokens