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 rules/krishnanpandya007/support-technician-setup/integrating-support-agentgit clone --depth 1 https://github.com/krishnanpandya007/support-technician-setupWrote 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/rules/krishnanpandya007/support-technician-setup/integrating-support-agent)<a href="https://agentmods.dev/rules/krishnanpandya007/support-technician-setup/integrating-support-agent"><img src="https://agentmods.dev/badge/rules/krishnanpandya007/support-technician-setup/integrating-support-agent.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 5.1 | $0.00116 | $0.02588 |
| Opus 5 | $0.00058 | $0.01294 |
| Sonnet 5 | $0.00023 | $0.00518 |
| Haiku 4.5 | $0.00012 | $0.00259 |
Grade A, and why
integrating-support-agent 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 5d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integrating the Support Agent
Overview
This is the last mile. The earlier stages produce a support kit; the operator then runs support-binder, applies the access migration, and fills .secrets — all locally, off-model. This skill takes that bound kit and the operator's end-user app and wires the two together, turning the kit's command-line runtime into a support endpoint real users reach from inside the app.
Core principle: follow the operator's practice; enforce the invariants regardless of it. Teams host things differently — a separate small service, a route inside the app, a serverless function, or an existing chat/helpdesk platform. This skill never prescribes a topology. It discovers the app's practice, confirms it, and generates the integration for that practice — while the five invariants below hold under every one of them. The repo-root INTEGRATION.md is the operator-facing companion: it explains the practices and their trade-offs in plain language; point the operator at it whenever a choice is theirs to make.
Prerequisites — stop and say so if missing: a complete support kit (harness/, tools/, runbooks/, persona.md, support.config.yaml); evidence the operator has done the local DB step (tools/ACCESS_SETUP.md and the *.local.* artifacts exist — you never read their contents beyond confirming presence); and the end-user app's source.
Universal vs practice-specific
Some artifacts are identical for every practice; generate them always. The rest exist only for the confirmed practice — never generate all variants speculatively.
| Always (universal) | Per-practice only |
|---|---|
| Chat endpoint contract (request/response + fail-closed rules) | Serving-layer code (service / route / function / platform adapter) |
| Session-bridge contract (verified session → user id → per-connection identity) | Session-bridge implementation (reuses the app's own verification) |
| Escalation wiring spec + fire-test script | End-user entry point (widget snippet / component edit / platform binding) |
SMOKE.md checklist + operator-run scripts |
Deployment glue (compose service / route registration / function config / platform setup) |
CHANGES.md review manifest |
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.
- 5d ago First seen · 112 lines · 2,588 tokens per session scan A 5e3ad63a645b
integrating-support-agent is a cursor rule published in the GitHub repository krishnanpandya007/support-technician-setup (2 stars, last pushed 2mo ago), licensed MIT. It adds 116 tokens to every session and 2,588 once invoked, about $0.0006 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.