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.
curl -O https://raw.githubusercontent.com/ProjectSidewalk/SidewalkWebpage/develop/CLAUDE.mdgit clone --depth 1 https://github.com/ProjectSidewalk/SidewalkWebpageWrote 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/instructions/projectsidewalk/sidewalkwebpage/claude-md)<a href="https://agentmods.dev/instructions/projectsidewalk/sidewalkwebpage/claude-md"><img src="https://agentmods.dev/badge/instructions/projectsidewalk/sidewalkwebpage/claude-md/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/instructions/projectsidewalk/sidewalkwebpage/claude-md"><img src="https://agentmods.dev/badge/instructions/projectsidewalk/sidewalkwebpage/claude-md.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 | $0.02986 | $0.02986 |
| Opus 5.5 | $0.01194 | $0.01194 |
| Sonnet 5.5 | $0.00597 | $0.00597 |
| Haiku 4.5 | $0.00299 | $0.00299 |
Grade A, and why
SidewalkWebpage CLAUDE.md scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
line above its `conf/routes` entry, or the CSRF filter 403s every real request while curl tests look fine. How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Sidewalk is a web-based crowdsourcing tool for mapping and assessing sidewalk accessibility. Scala 3.9 +
Play 3.0 (Java 17) backend, Postgres + PostGIS via Slick, and a vanilla-JS frontend of ES modules that Vite bundles
per page (no framework, no transpile), all run in Docker. Request flow is routes → Controller → Service → Table
(DAO). Architecture tour: docs/architecture.md. Setup, daily commands, troubleshooting: docs/dev-environment.md.
🚨 NEVER READ docker-compose.override.yml 🚨
Real live secrets, nothing enforces this but you. Never open it, never print or commit a value from it, and exclude
it from wide grep/find/cat * sweeps. Ask the maintainer for a value; docker-compose.yml has dummy equivalents.
Starting on an issue? Assign it first
The moment you begin implementing or debugging an issue (not when filing, reading, or triaging it), assign the
developer you act for: gh issue edit <n> --add-assignee @me. Assignment means "someone is on this now", so it is
never done at filing time and never skipped. If someone else is already assigned, say so before adding yourself.
This file holds only cross-cutting rules. .claude/rules/ surfaces path-scoped essentials when you touch a matching
file, and this table says which doc to read first:
| Working on… | Read first |
|---|---|
A schema change (conf/evolutions/) |
docs/evolutions.md |
A /v3/api endpoint or app/models/api/ |
docs/architecture.md → "The public API" (and the update-apis skill) |
Translations (conf/messages/, public/locales/) |
docs/internationalization.md |
| CSS, Twirl views, any UI | docs/style-guide.md, docs/accessibility.md |
| A new or changed user interaction | docs/logged-events.md |
Which labels Validate serves (ValidationQueuePolicy, the Validate queries) |
docs/validation-queue.md |
| Releases, deploys, asset caching, persistent media dirs | docs/deployment-and-stages.md |
| Routes, regions, or which streets a mission or walk may contain | docs/architecture.md → "Streets, regions, and routes" |
| Storing uploaded media (DB row vs. media dir) | docs/architecture.md → "Media storage" |
Label crops, or a marker drawn on one (label_crop provenance, #2660) |
docs/architecture.md → "Media storage" |
| Tests or CI | docs/testing-and-ci.md, test/e2e/README.md |
A script under scripts/ or tools/ |
tools/README.md |
| Onboarding a new city (streets, regions, schema, configs) | docs/onboarding-a-city.md (and the onboard-city skill) |
| Google Maps keys, quotas, or a Google Cloud bill | docs/google-cloud.md |
| The label lat/lng estimator or the labeling viewport frame | docs/label-latlng-estimation.md |
Street gradient / slope (street_gradient, tools/city/street_gradient.py) |
docs/street-gradient.md |
Which OSM ways a street lies on (osm_way_street_edge, tools/city/osm_lineage.py) |
docs/architecture.md → "Streets, regions, and routes" |
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.
- today Changed · +2 lines · +54 tokens per session acd60e2862f2
- yesterday Changed · +1 lines · +35 tokens per session ee613dceef9a
- 7d ago Changed · +1 lines · +30 tokens per session e917113481e5
- 14d ago Changed · +2 lines · +58 tokens per session 2a2baf3c0e12
- 20d ago Changed · -1 tokens per session c1885db3c7eb
- 21d ago Changed · +1 tokens per session 21f231f73151
- 23d ago Changed · +6 tokens per session 6383088878a5
- 27d ago Changed · +1 lines · +33 tokens per session 923aebe70128
- 28d ago Changed · +3 lines · +69 tokens per session 8e9d00306b46
- 29d ago First seen · 134 lines · 2,701 tokens per session scan A 7f94d09f4f94
SidewalkWebpage CLAUDE.md is an instructions file published in the GitHub repository ProjectSidewalk/SidewalkWebpage (111 stars, last pushed today), licensed MIT. It adds 2,986 tokens to every session, about $0.0119 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.