Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/reallygood83/teachermall-mcp/tcv)<a href="https://agentmods.dev/skills/reallygood83/teachermall-mcp/tcv"><img src="https://agentmods.dev/badge/skills/reallygood83/teachermall-mcp/tcv/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/reallygood83/teachermall-mcp/tcv"><img src="https://agentmods.dev/badge/skills/reallygood83/teachermall-mcp/tcv.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 | $0.00083 | $0.00793 |
| Opus 5 | $0.00042 | $0.00396 |
| Sonnet 5 | $0.00017 | $0.00159 |
| Haiku 4.5 | $0.00008 | $0.00079 |
Grade A, and why
tcv 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 9d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TCV 티처몰 쇼핑 어시스턴트
Use this skill when the user wants 티처몰 product search, classroom supplies, lesson materials, reward-system kits, budget shopping lists, or invokes /tcv, $tcv, or tcv.
This is the Codex counterpart to the Claude Code /tcv command. In Codex, prefer $tcv ... or tcv ...; if the interface passes /tcv as text, treat it exactly the same way.
Primary Rule
Use the teachermall MCP server tools whenever available. Do not answer from generic memory when live product links, prices, or availability matter.
The MCP server is expected at:
[mcp_servers.teachermall]
command = "node"
args = ["/Users/moon/Downloads/teachermall-mcp-main/dist/index.js"]
If the MCP tools are not visible in the current Codex session, tell the user to restart Codex once, then continue with the best available fallback only if they explicitly want a non-live draft.
Tool Selection
- Specific lesson/topic materials: call
recommend_for_lesson. - Classroom/reward kit: call
build_classroom_kit. - Semester-wide preparation list: call
generate_semester_preparation_list. - Multiple needs plus a budget: call
optimize_within_budget. - Lesson plan text to shopping list: call
create_shopping_list_from_text. - Simple product keyword lookup: call
search_products. - Specific product number/detail: call
get_product_details.
Output Requirements
Every product must include:
- Product name.
- Price.
- Purchase link as a visible raw URL line:
구매 링크: https://... - Popularity/purchase count if the MCP result provides it.
Do not rely only on a markdown-linked product name. Keep the raw purchase URL because the user explicitly wants buyable links to always be present.
Response Style
- Reply in Korean unless the user asks otherwise.
- Be practical for teachers: grade, budget, lesson purpose, classroom workflow, and excluded items matter.
- When budget is given, mention total cost and remaining budget if the MCP result provides them.
- If results look off-topic, refine the query and call another relevant MCP tool rather than accepting weak first-pass results.
- Before recommending purchase, remind briefly to verify option, quantity, delivery, and seller details on the actual product page when relevant.
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.
- 9d ago First seen · 76 lines · 83 tokens per session scan A 5b355f4536a9
tcv is a skill published in the GitHub repository reallygood83/teachermall-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 793 once invoked, about $0.0004 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
vertical-retail
Retail & e-commerce domain knowledge for SMB storefront products (storefront, inventory, pricing, cart-recovery). Codifies the vocabulary (SKU vs variant, reorder point, COGS/margin, ATS, AOV), the non-obvious rules (Shopify owns the storefront — don't fight it head-on; the wedge is multichannel inventory + reorder…
b2c-docs
Search and read B2C Commerce documentation using the b2c CLI. Covers Script API reference (dw. classes/modules), Developer Center guides (Commerce API, PWA Kit, SFRA, Storefront Next, B2C Commerce), Salesforce Help (Business Manager administration and merchandising), tooling documentation (CLI/MCP/SDK), standard job…
vertical-restaurants
Domain-knowledge primer for the restaurants & hospitality vertical (dine-in, pickup, delivery). Gives architect and pm the vocabulary, non-obvious operating rules, must-model entities, and incumbent landscape so a restaurant-product spec isn't naive about modifiers, 86'd items, aggregator commissions, tip law, and…
sealeap-xiezhi-amazon-product-knowledge-map-building
Build an Amazon product, audience, and use-case knowledge map before making product decisions. Use when a beginner lacks product ideas, rejects unfamiliar items too quickly, or needs a disciplined discovery routine.
learndash-woocommerce-access
Build or audit the LearnDash WooCommerce integration that grants/revokes LearnDash course and group access from WooCommerce products, orders, refunds, subscriptions, switches, and order-item changes. Use when code mentions learndash-woocommerce, relatedcourse, relatedgroup, LearnDash\WooCommerce\Settings\StatusAccess…
pool-manager
Gestion de pools de sous-agents pré-instanciés pour performance et réutilisation. Se déclenche avec "pool agent", "agent pool", "pool de sous-agents", "pre-allocated agents", "agent reuse", "warm agents", "agent cache", "worker pool agents". Couvre sizing, checkout/checkin, state reset, health monitoring, auto-scaling…