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 AlpacaLabsLLC/skills-for-architects --skill site-visit-reportgit clone --depth 1 https://github.com/AlpacaLabsLLC/skills-for-architectsWrote 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/alpacalabsllc/skills-for-architects/site-visit-report)<a href="https://agentmods.dev/skills/alpacalabsllc/skills-for-architects/site-visit-report"><img src="https://agentmods.dev/badge/skills/alpacalabsllc/skills-for-architects/site-visit-report/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/alpacalabsllc/skills-for-architects/site-visit-report"><img src="https://agentmods.dev/badge/skills/alpacalabsllc/skills-for-architects/site-visit-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 16 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Agent Snooping · line 86 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00087 | $0.02052 |
| Opus 5 | $0.00044 | $0.01026 |
| Sonnet 5 | $0.00017 | $0.00410 |
| Haiku 4.5 | $0.00009 | $0.00205 |
Grade A, and why
site-visit-report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/as:site-visit-report — Typed Field Evidence
Harness note: use
/as:<skill>on Claude Code and$<skill>on Codex. Resolve<skill-root>as the directory containing this loadedSKILL.mdand<plugin-root>as the plugin root that containsskills/, and use equivalent native tools when host tool names differ.
Create an auditable record of a site visit without turning limited observation, hearsay, or interpretation into verified professional conclusions.
Usage
/as:site-visit-report from field-notes/2026-07-21.md
/as:site-visit-report document today's walkthrough and attached photos
/as:site-visit-report revise site-reports/2026-07-21-roof-walkthrough.md
Hard rules
- Classify every substantive item. Keep direct observations, participant-reported information, interpretation, issues, and proposed follow-ups separate.
- State the observation boundary. Record access, visibility, weather, destructive-testing, equipment, and document limitations. An inaccessible or concealed area is
Not observed, never “no issue observed.” - Do not claim concealed-condition certainty. Report only visible conditions within the stated visit scope. Do not infer what is behind finishes, underground, inaccessible, or otherwise concealed.
- Do not claim compliance. Never declare code, zoning, life-safety, structural, MEP, accessibility, environmental, or contractual compliance. Route analysis to the appropriate specialist workflow and licensed professional.
- Save before promotion. Complete and save the report before offering follow-up. Saving must not create or modify
PROJECT.md,decisions/*.md, orTASKS.md. - Promote item by item. Require exact labels for every proposed fact, durable decision, or task; approval of the report as a whole is not promotion approval.
- Preserve dates and provenance. Distinguish visit date, created date, source date, and photo/file metadata. Store project-relative links rather than absolute machine paths.
- Never overwrite implicitly. Use deterministic numeric suffixes for collisions. Revise an existing report only when the user explicitly requests that exact revision.
- Do not fabricate gaps. Unknown participants, locations, dates, conditions, photo identities, owners, or due dates remain
Unknown,Not recorded, orNot observed.
What ships with it
2 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.
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.
- 12d ago First seen · 130 lines · 87 tokens per session scan A 3c59a513eba7
site-visit-report is a skill published in the GitHub repository AlpacaLabsLLC/skills-for-architects (353 stars, last pushed 9d ago), licensed MIT. It adds 87 tokens to every session and 2,052 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
cre-development
CRE Development and Construction suite - 8 specialist skills for U.S. site/entitlement screening, budget and yield-on-cost, construction loan sizing, GC contracts, draw review, schedule risk, lease-up pro forma, and IC memo writing.
github-issue-planning
Issue-backed plan persistence on GitHub via one managed issue comment with an idempotent marker. Prefers GitHub MCP when available and falls back to gh CLI when MCP is unavailable or misconfigured. Uses local plan persistence only when issue persistence is unavailable or not desired.
technical-roadmap-planning
Gathers inputs, defines initiatives, prioritises with an impact/effort matrix, sequences dependencies, and produces a roadmap table. Invoked when the user asks to plan a technical roadmap, prioritise engineering initiatives, or create a quarter/half-year engineering plan.
module-federation-ssr
Add, review, or debug server-side rendered Module Federation applications, including Modern.js, Nuxt, Next.js legacy Pages Router, Vinext, Vite SSR, and dual browser/server remote artifacts.
codex-symphony
Install and operate a portable OpenAI Symphony + Linear orchestration setup in any Git repository. Use when the user wants a one-command local Symphony runner, a reusable WORKFLOW template, background launch scripts, or a Codex wrapper that restarts Symphony automatically when reopening the CLI.
sparc-pipeline
Use when you need to run the full 5-phase SPARC methodology (Specification→Pseudocode→Architecture→Refinement→Completion) for a complex feature. Each phase has explicit done-criteria gates.