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.
git clone --depth 1 https://github.com/WYRE-AI/msp-claude-pluginsWrote 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/commands/wyre-ai/msp-claude-plugins/find-contact)<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/find-contact"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/find-contact/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/commands/wyre-ai/msp-claude-plugins/find-contact"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/find-contact.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 | $0.00015 | $0.00570 |
| Opus 5 | $0.00008 | $0.00285 |
| Sonnet 5 | $0.00003 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
find-contact 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 10d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find Contact
Resolve who a phone identifier belongs to inside 3CX — by email address, exact extension, or name — checking exact-match lookups first and falling back to phonebook and CRM-integrated contact search.
Prerequisites
- A 3CX PBX connected (directly or through Conduit's BYO connector) with a
valid, authenticated MCP session — see the
api-patternsskill - The identifier's type known ahead of time if possible: email, extension number, or name — this changes which lookup to try first
Steps
-
Try the exact-match lookup that fits the identifier
If given an email address, use the find-contact-by-email capability. If given a number that looks like an extension, use the find-contact-by-exact-extension capability. Exact-match lookups don't fuzzy match, so a wrong or partial extension returns nothing rather than a close guess.
-
Fall back to phonebook and CRM search on a miss, or if given a name
Search 3CX phonebooks and search CRM-integrated contacts in parallel. Treat an empty CRM-integrated result as "not synced on this PBX," not "doesn't exist in the CRM" — see the
directoryskill for why. -
If still unresolved, list PBX users/extensions
Useful when the identifier is close to a known extension but doesn't match exactly, or when confirming a name against the raw user list.
-
Report what was found
State which lookup resolved it (email match, extension match, phonebook, or CRM sync) so the requester knows how current the result is — a CRM-synced match is only as fresh as that PBX's CRM connector.
Examples
/find-contact [email protected]
/find-contact 1042
/find-contact "Jane Smith"
Error Handling
- No match anywhere: Confirm the identifier's exact spelling/format with the requester before concluding the contact doesn't exist — exact lookups are unforgiving of typos.
- CRM-integrated search returns nothing but the contact should exist in the CRM: That PBX's CRM connector may not be configured or may be stale — this is a sync-scope limitation, not proof the contact is missing from the CRM itself.
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.
- 10d ago First seen · 68 lines · 15 tokens per session scan A 371ca78a61f6
find-contact is a command published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 7d ago), licensed Apache-2.0. It adds 15 tokens to every session and 570 once invoked, about $0.0001 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 commands, from other repositories
analyze-java-domain
A code-analysis command for examining business rules and workflows in older Java Spring Boot projects. Spring Boot is a framework for building Java applications.
routes
List all REST endpoints in the Spring Boot project — scans controllers and prints a route table.
multi-backend
Backend-focused workflow (Research → Ideation → Plan → Execute → Optimize → Review), Codex-led.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.