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.
npx skills add jammaru/theapps-mcp --skill apps-manage-couponsgit clone --depth 1 https://github.com/jammaru/theapps-mcpWrote 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/jammaru/theapps-mcp/apps-manage-coupons)<a href="https://agentmods.dev/skills/jammaru/theapps-mcp/apps-manage-coupons"><img src="https://agentmods.dev/badge/skills/jammaru/theapps-mcp/apps-manage-coupons/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/jammaru/theapps-mcp/apps-manage-coupons"><img src="https://agentmods.dev/badge/skills/jammaru/theapps-mcp/apps-manage-coupons.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 | $0.00064 | $0.00495 |
| Opus 5.5 | $0.00026 | $0.00198 |
| Sonnet 5.5 | $0.00013 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
apps-manage-coupons 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.
What it actually says
Manage Apps coupons
Create and maintain discount codes with an explicit payment scope. Read references/coupons.md before constructing a body.
When to load this skill
Read this skill before the first matching apps_* MCP call in each task. Read the linked reference before every create, update, or delete operation.
Create
- Call
apps_auth_statusandapps_list_couponsto detect code collisions. - Establish the coupon name, customer-facing code, live or test payment mode, discount type and value, validity period, usage limit, payment type, and target products or plans.
- Treat
stripe_env_id: "1"as a test-mode coupon setting, not an API sandbox. The coupon is still created in the connected Apps account. - Build the smallest body accepted by the MCP schema.
- Call
apps_create_couponwithdry_run: true. - Explain the target scope and whether omitting
product_idsaffects every product or plan in that payment type. - Execute with
confirm: trueonly after approval. - Return the coupon identifier, code, discount, validity, usage limit, and target scope.
Update and delete
Fetch with apps_get_coupon first. Respect immutable fields and usage-history restrictions in the reference. Preview apps_update_coupon or apps_delete_coupon, explain revision or deletion behavior, and execute only after approval.
Safety and boundaries
- Writes need
APPS_MCP_ALLOW_WRITE=true. Do not ask the user to paste that value in chat; point them toconfigureor the MCP env. - Preview with
dry_run: true, explain the pending effect, then execute withconfirm: trueonly after approval. - Creating a coupon does not automatically attach it to a single page; scope comes from
payment_typeandproduct_ids. - Do not claim that a coupon is usable on a page unless the returned scope includes that page.
- Do not include purchaser or customer records in the result.
What ships with it
2 files 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.
- 2mo ago First seen · 36 lines · 64 tokens per session scan A 336733fb7631
apps-manage-coupons is a skill published in the GitHub repository jammaru/theapps-mcp (2 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 495 once invoked, about $0.0003 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.
apps-manage-coupons compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| apps-manage-couponsjammaru/theapps-mcp | Skill | 2 | 2d ago | MIT | A | 64 | Codex |
| amazon-reviews-api-skillbrowser-act/skills | Skill | 6.3k | 3d ago | MIT | A | 124 | Claude Code, Codex |
| amazon-competitor-analyzerbrowser-act/skills | Skill | 6.3k | 3d ago | MIT | A | 48 | Claude Code, Codex |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | today | MIT | A | 60 | Claude Code |
| external-purchasesrshankras/claude-code-apple-skills | Skill | 867 | today | MIT | A | 76 | Claude Code |
| food-orderBitterbot-AI/bitterbot-desktop | Skill | 2.5k | today | MIT | A | 53 | Claude Code, Codex |
| Product Photoshoot Workflowjau123/MeiGen-AI-Design-MCP | Skill | 1.8k | yesterday | MIT | A | 111 | Claude Code |