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 anysiteio/agent-skills --skill anysite-crm-auditgit clone --depth 1 https://github.com/anysiteio/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/anysiteio/agent-skills/anysite-crm-audit)<a href="https://agentmods.dev/skills/anysiteio/agent-skills/anysite-crm-audit"><img src="https://agentmods.dev/badge/skills/anysiteio/agent-skills/anysite-crm-audit/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/anysiteio/agent-skills/anysite-crm-audit"><img src="https://agentmods.dev/badge/skills/anysiteio/agent-skills/anysite-crm-audit.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 | $0.00818 |
| Opus 5 | $0.00055 | $0.00409 |
| Sonnet 5 | $0.00022 | $0.00164 |
| Haiku 4.5 | $0.00011 | $0.00082 |
Grade A, and why
anysite-crm-audit 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRM Audit
The safe first date with a user's CRM: read everything, write nothing, show what's broken
and what enrichment would fix. Also the natural funnel into anysite-crm-enrich.
Prerequisites
Active CRM connection. No profile needed (works better with one — gap analysis follows the mapped fields).
Flow
1. Inventory
crm_get_schema(object_type="contacts") / (object_type="companies")
Use properties filtering when you only need specific fields — the full schema is large.
Then page through records:
crm_query_records(object_type=..., properties=[key fields], after=<cursor>)
Audit scope: whole portal if small; else the working list + a stated sample. Say which.
2. Analyze (all local — no further API calls)
- Completeness: % filled per mapped/target field (email, title, company, domain, industry, size, linkedin_url). Rank by gap size.
- Match-key coverage: how many contacts have email / linkedin_url / neither (the "neither" group is unenrichable and un-dedupable — flag it).
- Duplicate candidates: same normalized email; same domain with several company records; same person name + company. Candidates only — never auto-merge.
- Email ↔ employer mismatch: contact's email domain vs their linked company's domain. A mismatch has THREE causes needing different handling (all seen live): the person changed jobs; the COMPANY rebranded/changed domain (old domain usually still receives mail — the contact is fine); or the email is genuinely stale. Free discriminator already in the data: if crunchbase under the domain-derived alias returns a different company NAME than the LinkedIn page of that same domain — that's a rebrand, not a departure. FLAG ONLY, never auto-fix in either direction — in two causes out of three there is nothing to "fix", and "correcting" the company from the email domain overwrites good data with stale. Job-change suspects go to anysite-crm-champions.
- Staleness: if
anysite_last_enriched_at(or similar) is mapped — age distribution; contacts with no activity fields; companies with dead domains (spot-check a few viawebparser/parseonly if the user asks). - Association health: contacts without a company link (visible as missing company fields when queried).
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 · 69 lines · 109 tokens per session scan A df1361c3a005
anysite-crm-audit is a skill published in the GitHub repository anysiteio/agent-skills (19 stars, last pushed 28d ago), licensed MIT. It adds 109 tokens to every session and 818 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 2026-08-30.
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…