Borrowing it
Nothing to install: this file belongs to krishnanpandya007/support-technician-setup. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/krishnanpandya007/support-technician-setup/master/.claude/skills/generating-support-persona/SKILL.mdgit 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/skills/krishnanpandya007/support-technician-setup/generating-support-persona)<a href="https://agentmods.dev/skills/krishnanpandya007/support-technician-setup/generating-support-persona"><img src="https://agentmods.dev/badge/skills/krishnanpandya007/support-technician-setup/generating-support-persona/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/krishnanpandya007/support-technician-setup/generating-support-persona"><img src="https://agentmods.dev/badge/skills/krishnanpandya007/support-technician-setup/generating-support-persona.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 | $0.00069 | $0.01057 |
| Opus 5 | $0.00034 | $0.00528 |
| Sonnet 5 | $0.00014 | $0.00211 |
| Haiku 4.5 | $0.00007 | $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 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 — 57 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 ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 57 lines · 0 tokens per session scan A cb210e5d83aa
generating-support-persona is a skill published in the GitHub repository krishnanpandya007/support-technician-setup (2 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 1,057 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 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…