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/AGENTS.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/instructions/krishnanpandya007/support-technician-setup/agents-md)<a href="https://agentmods.dev/instructions/krishnanpandya007/support-technician-setup/agents-md"><img src="https://agentmods.dev/badge/instructions/krishnanpandya007/support-technician-setup/agents-md.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 | $0.22692 | $0.22692 |
| Opus 5 | $0.11346 | $0.11346 |
| Sonnet 5 | $0.04538 | $0.04538 |
| Haiku 4.5 | $0.02269 | $0.02269 |
Grade A, and why
support-technician-setup AGENTS.md scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Every tool, regardless of `connection_type`, sits behind a single **StateAdapter** boundary — `fetch(tool, params, session) → summary`. This is the one reviewed place where read-only enforcement and **session-scoping** l How it starts
The opening of the file, as written. The whole thing — 984 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Support Technician — agent instructions
A methodology bundle that turns a codebase into a read-only customer-support agent: it diagnoses a user's live state through generated read-only tools and escalates a proposed fix to a human — it never mutates data itself.
When asked to build or set up a support agent, follow the staged methodology below. Each
stage's full procedure is embedded here, and also lives at bundle/skills/<name>/SKILL.md.
Build stages (skills)
- authoring-support-runbooks — Use when authoring the diagnostic runbooks a customer-support agent follows at runtime — turning a product's failure surface, its harness, and its read-only tool catalog into symptom-to-resolution decision trees plus synthetic evaluation tickets, for mandatory human review. Triggers: "author the support runbooks", "build the diagnostic decision trees", part of setting up a support agent.
- discovering-support-tools — Use when generating the read-only data-access tools a customer-support agent uses to diagnose an end user's live state — reading a project's backend to propose a tool catalog plus the database access SQL (restricted read-only role, column grants, row-level security), for mandatory human review. Triggers: "discover support tools", "generate the read-only tools / DB access for the support agent", part of setting up a support agent.
- generating-codebase-harness — Use when turning a codebase into a sanitized plain-language help-center knowledge base ("harness") for an AI support assistant — reading one or more project roots and producing navigable Markdown that describes user-facing behavior with no technical detail and no security mechanisms or secrets. Triggers: "build a harness", "help-center knowledge base from code", "sanitized docs for a support bot".
- generating-support-persona — Use when generating a project-specific customer-support assistant persona from the reference template — turning a harnessed product's knowledge base and tool catalog into a finished persona.md for the runtime support agent. Triggers: "generate the support persona", "make the assistant persona for ", part of setting up a support agent.
- integrating-support-agent — Use to integrate a built support kit into the operator's real end-user app — discovers the app's own serving, session, frontend, and deployment practice and generates, for that practice, the session bridge (verified user id → per-connection identity), the chat serving layer, the end-user entry point, real escalation wiring, deployment glue, and an operator-run smoke-test checklist, all for mandatory human review. Triggers: "integrate the support agent", "wire the support kit into my app", "add the support chat to ", "deploy the support agent".
- setting-up-support-agent — Use to set up a full customer-support agent for a web app — orchestrates the whole build pipeline (knowledge base, read-only tools + access SQL, diagnostic runbooks, persona, config/secrets scaffolding) by running the four stage skills in order, with a human-review gate after each, and hands off the local database step to the support-binder CLI. Triggers: "set up a support agent for ", "stand up the support kit", "build the full support pipeline".
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.
- 6d ago First seen · 984 lines · 22,692 tokens per session scan A 310f090ab49f
support-technician-setup AGENTS.md is an instructions file published in the GitHub repository krishnanpandya007/support-technician-setup (2 stars, last pushed 2mo ago), licensed MIT. It adds 22,692 tokens to every session, about $0.1135 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.