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/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/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/rules/krishnanpandya007/support-technician-setup/integrating-support-agent"><img src="https://agentmods.dev/badge/rules/krishnanpandya007/support-technician-setup/integrating-support-agent.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 | $0.00116 | $0.02588 |
| Opus 5.5 | $0.00046 | $0.01035 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 4mo ago), licensed MIT. It adds 116 tokens to every session and 2,588 once invoked, about $0.0005 per session on Opus 5.5. 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
api-property-optionality-hygiene
Fix ApiProperty/ApiPropertyOptional optionality mismatches in DTO files; use for scheduled batch fixes or DTO edits.
python
Python best practices and patterns for modern software development with Flask and SQLite.
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
django
Definitive guidelines for writing maintainable, performant, and secure Django applications, emphasizing modern best practices, clear code organization, and efficient patterns.
selectools-providers
Rules for working with LLM provider adapters in selectools.
ehs-ims-conventions
EHS IMS app — RBAC, data layer, tRPC, migrations, AI boundaries.