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/generating-support-persona)<a href="https://agentmods.dev/rules/krishnanpandya007/support-technician-setup/generating-support-persona"><img src="https://agentmods.dev/badge/rules/krishnanpandya007/support-technician-setup/generating-support-persona.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 | $0.00063 | $0.01058 |
| Opus 5 | $0.00032 | $0.00529 |
| Sonnet 5 | $0.00013 | $0.00212 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
generating-support-persona 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 7d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generating a Support Persona
Overview
The runtime customer-support agent loads a persona that fixes its identity, voice, and — most importantly — its safety boundaries. You produce a project-specific persona.md by filling the reference template in templates/persona.reference.md from the harnessed product. You are the generator described in that template's GENERATION CONTRACT.
Core principle: tone and scope are tailored per project; the safety invariants are copied verbatim and never softened.
Inputs
- The end-user KB harness for the product (
index.md+ articles). (The end-user app — not an internal/admin tool. If only an admin harness exists, stop and say the end-user harness is required first.) - The generated tool catalog (for
{{support_scope}}/{{key_entities}}), if available. - The product's
support.config.yaml(for{{user_followup_channel}}), if available. templates/persona.reference.md(in this skill folder).
The hard rules
[LOCKED]blocks are copied verbatim. Privacy/security boundaries, the read-only/escalate-only Actions block, refusals/honesty, and the Never list must appear unchanged in every persona, for every project. Do not reword, soften, merge, or drop them. These are the safety contract.{{slots}}are filled only from real project facts. Derive each from the inputs per its<!-- GEN ... -->note. If a slot can't be grounded, use the conservative fallback in the note — never invent product facts, amounts, dates, or policies.[TUNABLE]blocks may be rephrased, not re-scoped. Adjust register to the domain (casual for consumer apps, formal for finance/health); keep the intent and every bullet.- Strip all
<!-- GEN ... -->and contract comments from the generated file. The output is clean Markdown the agent reads. - Scope is end-user only.
{{support_scope}}lists user-facing capabilities from the end-user harness — never admin-only or internal capabilities, never how anything is built or secured (inherit the harness's no-technical-detail rule). - Examples read natively. Regenerate the example phrasings using the product's real domain nouns (from the tool catalog / harness), one per category (resolved, need-info, escalating, don't-know). Use placeholders for specific values, not invented ones.
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.
- 7d ago First seen · 58 lines · 1,058 tokens per session scan A d9917b22025d
generating-support-persona is a cursor rule published in the GitHub repository krishnanpandya007/support-technician-setup (2 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 1,058 once invoked, about $0.0003 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.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.