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 adbertram/cli-tools --skill nextdoor-cligit clone --depth 1 https://github.com/adbertram/cli-toolsWrote 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/adbertram/cli-tools/nextdoor-cli)<a href="https://agentmods.dev/skills/adbertram/cli-tools/nextdoor-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/nextdoor-cli/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/adbertram/cli-tools/nextdoor-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/nextdoor-cli.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 | $0.00143 | $0.01540 |
| Opus 5.5 | $0.00057 | $0.00616 |
| Sonnet 5.5 | $0.00029 | $0.00308 |
| Haiku 4.5 | $0.00014 | $0.00154 |
Grade A, and why
nextdoor-cli 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 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.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<quick_start>
The nextdoor CLI exposes top-level data commands plus auth and cache
subapps:
nextdoor <command> [arguments] [options]
| Task | Command |
|---|---|
| Check auth status | nextdoor auth status |
| Login to Nextdoor | nextdoor auth login |
| View feed | nextdoor feed --limit 25 |
| Browse For Sale & Free listings | nextdoor classifieds list --limit 25 |
| Keyword-search listings | nextdoor classifieds list "lego" --limit 25 --filter "type:eq:ORGANIC,title:contains:lego" |
| Get one listing's full detail | nextdoor classifieds get <listing-uuid> |
| Search all Nextdoor content | nextdoor search "<query>" --limit 25 |
| View notifications | nextdoor notifications --table |
| Get current user | nextdoor me --table |
| List profiles | nextdoor auth profiles list |
All data commands support --table/-t, --properties/-p, and (except me)
--filter/-f and --limit/-l. feed and classifieds list also support
--sort/-s (newest default, relevance) and --desc/-d.
</quick_start>
<listing_urls>
Use classifieds list when the task needs a verified direct listing URL.
It is the only command backed by Nextdoor's dedicated For Sale & Free surface,
and every type: ORGANIC row returns a real url
(https://nextdoor.com/for_sale_and_free/<uuid>/?init_source=search) plus
price. Sponsored grid slots come back with all listing fields null — filter
them out with --filter "type:eq:ORGANIC".
feed rows also carry url, the post's permalink
(https://nextdoor.com/p/<slug>?view=detail). These slugs are opaque and exist
only in the API response — never construct a Nextdoor URL from an id.
PROMO rows have no permalink and report url: null.
The general feed mixes classifieds in with neighborhood news at roughly
5-10% of items and has no classified type filter, so do not use it to harvest
listings — use classifieds list.
</listing_urls>
<keyword_search_is_not_a_filter>
classifieds list <query> is a relevance signal, not a filter. Never trust
it to restrict results to the keyword.
The query IS wired through — it is sent verbatim as
classifiedSearchArgs.query on Nextdoor's own For Sale & Free search. That is
proven, not assumed: a nonsense token returns zero rows.
nextdoor classifieds list "zzzzznotarealthing" # -> 0 rows (query reaches the server)
What Nextdoor does with it is the problem. Its classifieds search ranks by relevance and applies no relevance floor, so it pads thin result sets with unrelated listings instead of returning fewer rows:
| Query | What comes back |
|---|---|
wheelchair (real local inventory) |
"Electric Wheelchair", "Lightweight Transport Wheelchair" — plus "Burgundy Sofa", "Chicago Cubs Office Chair" |
lego / legos (no local inventory) |
100% padding: "Vintage Secretary Desk", "New Xbox Series S Bundle", "Everest & Jennings Transport Wheelchair" |
The padding is also unstable: the same keyword returned 2, 3, and 4 rows on consecutive runs. Nextdoor exposes no exact-match flag and no relevance threshold on this operation, so there is nothing to turn off.
Post-filter every keyword search, and put the conditions in ONE --filter:
nextdoor classifieds list "lego" --limit 50 \
--filter "type:eq:ORGANIC,title:contains:lego"
Repeating --filter is OR, not AND — --filter "type:eq:ORGANIC" --filter "title:contains:lego" keeps every sponsored-free row regardless of title.
Comma-separated conditions inside a single --filter are AND.
A keyword search that returns zero rows after post-filtering is the honest answer: Nextdoor has no local listing for that term. Do not read the unfiltered padding as inventory. </keyword_search_is_not_a_filter>
<essential_principles>
MANDATORY: Consult the adjacent usage.json at <cli-tools-root>/_repo/skills/<tool>-cli/usage.json before executing ANY nextdoor command.
This file contains complete command syntax, all arguments, all options, and usage instructions for every command. Never guess at command syntax.
What ships with it
1 file 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.
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 First seen · 132 lines · 143 tokens per session scan A 76ccc898f06a
nextdoor-cli is a skill published in the GitHub repository adbertram/cli-tools (6 stars, last pushed today), licensed MIT. It adds 143 tokens to every session and 1,540 once invoked, about $0.0006 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 2026-11-07.
nextdoor-cli compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nextdoor-cliadbertram/cli-tools | Skill | 6 | today | MIT | A | 143 | Claude Code, Codex |
| opencli-autofixjackwener/OpenCLI | Skill | 31k | yesterday | Apache-2.0 | A | 61 | Claude Code |
| surfnicobailon/surf-cli | Skill | 684 | yesterday | MIT | A | 53 | Claude Code, Codex |
| rdc-cliBANANASJIM/rdc-cli | Skill | 193 | 14d ago | MIT | A | 82 | Claude Code, Codex |
| pixiv-cli-ciFlanChanXwO/pixiv-cli | Skill | 132 | yesterday | MIT | A | 61 | Codex |
| acrawl-mcpMingye-Lu/AgenticCrawler | Skill | 15 | yesterday | MIT | A | 200 | Claude Code, Codex |
| debug-hubrexleimo/aios | Skill | 62 | yesterday | MIT | B | 66 | Claude Code, Codex |