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 agentmods add skills/civicpatch/open-data/add-new-statenpx skills add CivicPatch/open-data --skill add-new-stategit clone --depth 1 https://github.com/CivicPatch/open-dataWhat 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 | $0.00072 | $0.01835 |
| Opus 5 | $0.00036 | $0.00918 |
| Sonnet 5 | $0.00014 | $0.00367 |
| Haiku 4.5 | $0.00007 | $0.00184 |
Grade A, and why
add-new-state 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
data = requests.get(url, headers=headers).json() How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a New State (steps 1-4)
Covers the manual prep before the full mise run setup-state run. Full reference: DEVELOPMENT.md → "Adding a new state". This skill only does steps 1-4; stop after the dry-run and hand back to the user for step 5 onward (they'll want to review results before the full run, county-conversion decisions, PMTile regen, etc.).
Ask the user for the two-letter state code and full name if not given (e.g. va / Virginia).
Step 1 — Register the state
Read scripts/jurisdictions/config.py fully first. Determine pull_from_census:
["places"]only — states where county subdivisions have no functioning government (statistical/MCD-less states). Most states default here.["places", "county_subdivisions"]— states with legally functioning MCDs (New England, NY, NJ, PA, MI, WI, MN, etc. — towns/townships that are themselves the unit of government, sometimes without a coextensive incorporated place).
If unsure which applies, say so and ask, or reason from Census Bureau MCD classification — don't guess silently.
Add the config block (match existing indentation/style exactly, including any quirks like extra leading spaces already present in neighboring entries). There is no import to add — states are pure data now:
"<state>": {
"fips": "<fips>",
"name": "<State Name>",
"pull_from_census": [...],
"local_wiki": {}, # filled in by step 2
"validation_sources": ["google"],
},
FIPS codes: look up the standard 2-digit state FIPS if not already known — don't guess.
Step 2 — Fit local_wiki to the list page
There is no per-state scraper. scripts/jurisdictions/scrapers/municipalities.py handles every state; local_wiki supplies only that state's deviations from the defaults. Read municipalities.py before doing anything here — it is ~60 lines and is the whole contract.
| key | default | set it when |
|---|---|---|
table_index |
0 |
the municipality table isn't the page's first wikitable |
rows_to_skip |
1 |
the header spans two rows (usually land area splitting into sq mi / km²) |
entry_column |
0 |
the place name isn't the first column |
title |
List_of_municipalities_in_<State_Name> |
that title is a disambiguation page (Georgia: the country vs the U.S. state) |
parser |
"table" |
"bullet_list" — the page has no wikitable, just per-letter div.div-col > ul > li bullets (North Carolina) |
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.
- 2d ago First seen · 116 lines · 72 tokens per session scan A 8fd03350f749
add-new-state is a skill published in the GitHub repository CivicPatch/open-data (5 stars, last pushed 5d ago), licensed CC0-1.0. It adds 72 tokens to every session and 1,835 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…