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 magnus919/agent-skills --skill raleighgit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/raleigh)<a href="https://agentmods.dev/skills/magnus919/agent-skills/raleigh"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/raleigh/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/magnus919/agent-skills/raleigh"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/raleigh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00109 | $0.03786 |
| Opus 5 | $0.00055 | $0.01893 |
| Sonnet 5 | $0.00022 | $0.00757 |
| Haiku 4.5 | $0.00011 | $0.00379 |
Grade A, and why
raleigh 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 9d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Raleigh Civic Data
A read-only CLI for the City of Raleigh's public civic data and services. It discovers datasets from the live ArcGIS Hub catalog, queries ArcGIS layers, exports imagery, geocodes and reverse-geocodes addresses, reads GoRaleigh GTFS and GTFS-Realtime feeds, searches the guest-public Permit and Development Portal, lists public RaleighNC.gov content, and extracts public eSCRIBE meetings.
All operations are read-only and use fixed endpoint contracts. HTTPS is required except for explicitly acknowledged RFD report lookups, whose upstream site supports only plain HTTP. No API key, sign-in, payment, or submission flow is implemented.
Quick Start
# List live datasets
scripts/raleigh catalog
# Search the catalog
scripts/raleigh search "food inspection"
# Show a dataset's live metadata
scripts/raleigh info "Raleigh Dog Parks"
# Query records
scripts/raleigh query "Food Inspections" --where "SCORE < 70" --limit 20
# Export to CSV
scripts/raleigh download "Raleigh Dog Parks" -f csv -o dog_parks.csv
Commands
Dataset discovery
| Command | Purpose | Example |
|---|---|---|
catalog |
List live Hub datasets | scripts/raleigh catalog --json |
search |
Search catalog metadata | scripts/raleigh search "building permit" --limit 10 |
info |
Show a dataset by title or ID | scripts/raleigh info "Raleigh Dog Parks" --json |
query |
Query records with filters | scripts/raleigh query "Food Inspections" --where "SCORE<70" --limit 20 |
download |
Export to CSV, GeoJSON, or JSON | scripts/raleigh download "Parcels" -f geojson -o parcels.geojson |
categories |
List categories from the catalog | scripts/raleigh categories |
catalog-check |
Validate cached endpoints | scripts/raleigh catalog-check --sample 10 |
Imagery
| Command | Purpose | Example |
|---|---|---|
imagery catalog |
List ImageServer services | scripts/raleigh imagery catalog --json |
imagery info |
Show service metadata | scripts/raleigh imagery info Orthos2025 |
imagery export |
Export bounded image | scripts/raleigh imagery export Orthos2025 --bbox=-78.7,35.7,-78.6,35.8 --size 400,400 -o ortho.jpg |
imagery identify |
Identify pixel value at point | scripts/raleigh imagery identify Orthos2025 --point=-78.65,35.75 |
imagery statistics |
Compute extent statistics | scripts/raleigh imagery statistics Orthos2025 --bbox=-78.7,35.7,-78.6,35.8 |
What ships with it
60 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.
- evals/evals.json 20 KB
- EVIDENCE-LEDGER.md 21 KB
- README.md 4.9 KB
- references/api-reference.md 2.1 KB
- references/civic-content-reference.md 1.8 KB
- references/dataset-catalog.md 731 B
- references/development-reference.md 1.4 KB
- references/fire-reference.md 10 KB
- references/fire-reports-reference.md 4.0 KB
- references/imagery-reference.md 1.3 KB
- references/incidents-reference.md 2.3 KB
- references/meetings-reference.md 1.3 KB
- references/police-reference.md 4.2 KB
- references/public-safety-statistics-reference.md 2.8 KB
- references/transit-reference.md 1.7 KB
- scripts/canary.py 22 KB runs code
- scripts/raleigh 615 B
- scripts/raleighlib/__init__.py 65 B runs code
- scripts/raleighlib/arcgis.py 11 KB runs code
- scripts/raleighlib/civic.py 14 KB runs code
- scripts/raleighlib/cli.py 73 KB runs code
- scripts/raleighlib/core.py 17 KB runs code
- scripts/raleighlib/development.py 14 KB runs code
- scripts/raleighlib/fire_protection.py 8.8 KB runs code
- scripts/raleighlib/fire.py 17 KB runs code
- scripts/raleighlib/geocode.py 6.4 KB runs code
- scripts/raleighlib/gtfs_realtime_pb2.py 20 KB runs code
- scripts/raleighlib/gtfs-realtime.proto 64 KB
- scripts/raleighlib/hub.py 10.0 KB runs code
- scripts/raleighlib/imagery.py 7.8 KB runs code
- scripts/raleighlib/incidents.py 6.0 KB runs code
- scripts/raleighlib/meetings.py 16 KB runs code
- scripts/raleighlib/police.py 8.3 KB runs code
- scripts/raleighlib/public_safety_stats.py 20 KB runs code
- scripts/raleighlib/rfd_reports.py 13 KB runs code
- scripts/raleighlib/transit.py 18 KB runs code
- tests/fixtures/escribe-agenda.html 343 B
- tests/fixtures/escribe-empty.html 110 B
- tests/fixtures/escribe-listing.html 221 B
- tests/fixtures/fire-reports-empty.json 17 B
- tests/fixtures/fire-reports-recent-lag.json 49 B
- tests/fixtures/fire-reports-results.json 501 B
- tests/fixtures/fire-reports-schema-drift.json 90 B
- tests/fixtures/fire-reports-service-error.json 74 B
- tests/fixtures/gtfs-realtime-empty.bin 13 B
- tests/fixtures/gtfs-realtime-malformed.bin 28 B
- tests/fixtures/gtfs-realtime-stale-alert.bin 44 B
- tests/fixtures/gtfs-realtime-stale.bin 13 B
- tests/fixtures/gtfs-realtime.bin 44 B
- tests/fixtures/gtfs.zip 1.1 KB
- tests/fixtures/published-fire-statistics.json 2.4 KB
- tests/fixtures/published-police-statistics.json 1.2 KB
- tests/fixtures/rfd-date-empty.html 234 B
- tests/fixtures/rfd-date-malformed.html 300 B
- tests/fixtures/rfd-date-markup-drift.html 76 B
- tests/fixtures/rfd-date-results.html 511 B
- tests/fixtures/rfd-error-page.html 93 B
- tests/fixtures/rfd-inspection-empty.html 167 B
- tests/fixtures/rfd-inspection-results.html 557 B
- tests/fixtures/rfd-narrative-result.html 285 B
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.
- 9d ago First seen · 222 lines · 109 tokens per session scan A 2013d63ed2c9
raleigh is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 3,786 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…