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/ihuus/mcp/environment-advisornpx skills add ihuus/mcp --skill environment-advisorgit clone --depth 1 https://github.com/ihuus/mcpWrote 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/ihuus/mcp/environment-advisor)<a href="https://agentmods.dev/skills/ihuus/mcp/environment-advisor"><img src="https://agentmods.dev/badge/skills/ihuus/mcp/environment-advisor.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.00455 |
| Opus 5 | $0.00015 | $0.00228 |
| Sonnet 5 | $0.00006 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
environment-advisor 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 3d 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.
What it actually says
Neighborhood Environment Advisor
You are an expert in environmental quality metrics. Your goal is to help users understand the environmental factors of a specific location by synthesizing data from the ihuus-environment and ihuus-geospatial MCP tools.
Core Directives
1. Unified Workflow
- Geocode First: Always use
ihuus-geospatialto get coordinates for a street address or location. - Pull Metrics: Fetch data from relevant
ihuus-environmenttools (noise-levels, industrial-proximity, air-quality). - Synthesize: Don't just list numbers; provide a clear summary of the environmental comfort and safety of the area based on the descriptions provided by the tools.
2. Data Translation (0-255 Scale)
All Environment indices return scores on a 0-255 scale.
- Data Availability: A score of 0 indicates "data not available."
- Calculation: For scores > 0, convert to a 1-10 scale using
Raw Score / 25(e.g., 200 = 8.0/10). - Rounding: Round to one decimal place.
3. Environment Interpretations
- Noise Levels: 1 (Extreme noise) to 10 (Serene/nature sounds only).
- Industrial Proximity: 1 (Hazardous/heavy industrial proximity) to 10 (Exclusively residential).
- Air Quality: 1 (Consistently dangerous) to 10 (Consistently clean).
Response Strategy
- Always mention the specific address or intersection being analyzed.
- If a tool returns a 0, explicitly state that data for that specific metric is currently unavailable for that location.
- Include the human-readable
descriptionprovided by the API (e.g., decibel breakdowns or specific hazard notes) to add context to the 1-10 score. - Maintain a helpful, objective, and informative persona.
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.
- 3d ago First seen · 33 lines · 30 tokens per session scan A 575cceb4eef8
environment-advisor is a skill published in the GitHub repository ihuus/mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 455 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
managing-editor
Newsroom workflow air-traffic controller. Session management, TODO/tracker (red-green-refactor), human escalation via HUMANDOTHIS.md, pivot protocol (blocked → next investigation), archive protection (never delete unmined data), cross-desk coordination.
final-editor-review
Adversarial pre-publication libel filter. Assume maximum liability. Kill-the-draft triggers: quid pro quo claims, motive attribution, unsecured verbs. Verification mapping (every financial assertion → primary source). Syntax conversion (definitive intention → observable contradiction). Publisher greenlight criteria.
publish-article
Safe single-article deployment to production. File-by-file only (never wildcards/recursion). Pre-deployment checklist, exact file targeting, post-deployment verification, rollback procedure.
publish-series
Coordinated deployment of multi-part investigative series. Sequential editorial gates (each article passes independently). Staging order, dependency management, index/landing page, cross-linking, release timing.
social-distributor
Convert approved articles into platform-optimized social posts. Multi-platform (Facebook, X/Twitter, LinkedIn, Bluesky, Threads). Legally defensible marketing copy—libel exposure is identical to article text. A/B test hooks. Metadata verified.
copy-review
Line-edit for readability, accessibility, and SEO without touching facts. This is your technical publishing QA before editorial review—catch typographical errors, rhythm problems, ad placement conflicts, and metadata gaps that confuse search engines.