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 veritrans/midtrans-agent-skills --skill integrate-midtrans-paymentsgit clone --depth 1 https://github.com/veritrans/midtrans-agent-skillsWrote 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/veritrans/midtrans-agent-skills/integrate-midtrans-payments)<a href="https://agentmods.dev/skills/veritrans/midtrans-agent-skills/integrate-midtrans-payments"><img src="https://agentmods.dev/badge/skills/veritrans/midtrans-agent-skills/integrate-midtrans-payments/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/veritrans/midtrans-agent-skills/integrate-midtrans-payments"><img src="https://agentmods.dev/badge/skills/veritrans/midtrans-agent-skills/integrate-midtrans-payments.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 | $0.00137 | $0.02341 |
| Opus 5.5 | $0.00055 | $0.00936 |
| Sonnet 5.5 | $0.00027 | $0.00468 |
| Haiku 4.5 | $0.00014 | $0.00234 |
Grade A, and why
integrate-midtrans-payments 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integrate Midtrans Payments
Operating Rule
Treat this as payment-system integration, not generic API wiring. Before changing code, learn the merchant's checkout architecture, payment products, persistence model, callback paths, auth/session boundary, environment management, deployment target, and test harness.
Before recommending a Midtrans product or writing code, complete the merchant readiness preflight: account state, sandbox credentials, active payment methods, expected customer flows, dashboard callback URLs, and the proof level the merchant expects. If those facts are missing and cannot be inferred from the project, pause and ask for them instead of silently assuming them.
Use current Midtrans docs each time. Search https://docs.midtrans.com/llms.txt first, then open product pages for the methods being implemented; llms.txt links the .md variant of every page — fetch those instead of the HTML.
Precedence: live docs.midtrans.com content wins over this skill for endpoints, parameters, field names, and product availability; this skill wins for integration discipline (state model, idempotency, signature hygiene, verification). Skill version 0.3.2, validated against docs.midtrans.com on 2026-06-25. If a current docs page contradicts this skill, follow the docs and ask the merchant to report the mismatch at https://github.com/veritrans/midtrans-agent-skills/issues.
Workflow
-
Run merchant readiness preflight
- Complete merchant-readiness-preflight.md before product choice or code.
- Infer from env, deploy config, runbooks, tests, provider code, and specs; ask only for missing blockers.
- Gate unavailable methods with configuration and state what dashboard/merchant action is still required.
-
Classify the integration
- Identify whether the merchant wants hosted checkout, custom UI, recurring/tokenized payments, marketplace/partner behavior, or a hybrid.
- Map each requested payment method to the intended Midtrans product before writing code.
- Do not mix Snap, Core API, and BI-SNAP request shapes, auth headers, callback semantics, or status objects.
- If the merchant need is unclear, read merchant-decision-tree.md and ask the smallest set of clarifying questions.
What ships with it
41 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.
- agents/openai.yaml 229 B
- assets/fixtures/bisnap-debit-notification.json 586 B
- assets/fixtures/bisnap-qris-notification.json 607 B
- assets/fixtures/bisnap-va-notification.json 651 B
- assets/fixtures/gopay-account-linking-notification.json 511 B
- assets/fixtures/payment-link-notification.json 971 B
- assets/fixtures/recurring-notification-card.json 1.2 KB
- assets/fixtures/snap-notification-expire.json 784 B
- assets/fixtures/snap-notification-partial-refund.json 990 B
- assets/fixtures/snap-notification-pending.json 809 B
- assets/fixtures/snap-notification-refund.json 978 B
- assets/fixtures/snap-notification-settlement.json 842 B
- assets/templates/env.example 3.6 KB
- evaluations.json 23 KB
- references/agent-portability.md 6.2 KB
- references/bisnap-core.md 18 KB
- references/core-api-classic.md 9.6 KB
- references/evaluation-prompts.md 20 KB
- references/gopay-tokenization.md 5.7 KB
- references/merchant-decision-tree.md 5.7 KB
- references/merchant-readiness-preflight.md 6.0 KB
- references/midtrans-runtime-patterns.md 6.1 KB
- references/mobile-sdk.md 7.7 KB
- references/operations-and-go-live.md 6.7 KB
- references/payment-links.md 5.9 KB
- references/project-adaptation.md 5.5 KB
- references/refund-operations.md 8.3 KB
- references/sandbox-interaction-helper.md 13 KB
- references/snap-checkout.md 22 KB
- references/subscriptions.md 8.2 KB
- references/verification-playbook.md 3.1 KB
- scripts/bisnap_timestamp.py 1.2 KB runs code
- scripts/dry_run_bisnap_sign.py 5.2 KB runs code
- scripts/format_partner_service_id.sh 1.5 KB runs code
- scripts/print_midtrans_webhook_ips.sh 4.9 KB runs code
- scripts/README.md 6.4 KB
- scripts/replay_snap_webhook.sh 6.8 KB runs code
- scripts/sign_bisnap_access_token.py 4.5 KB runs code
- scripts/sign_bisnap_transaction.py 4.3 KB runs code
- scripts/verify_bisnap_notification.py 5.2 KB runs code
- scripts/verify_snap_signature.sh 4.1 KB runs code
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 · 113 lines · 137 tokens per session scan A 60f8e7cbcb2a
integrate-midtrans-payments is a skill published in the GitHub repository veritrans/midtrans-agent-skills (12 stars, last pushed 4mo ago), licensed BSD-3-Clause. It adds 137 tokens to every session and 2,341 once invoked, about $0.0005 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.
integrate-midtrans-payments compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| integrate-midtrans-paymentsveritrans/midtrans-agent-skills | Skill | 12 | 4mo ago | BSD-3-Clause | A | 137 | Codex |
| asc-ppp-pricingrorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 45 | Claude Code |
| snaplii-cliSnaplii-Inc/agent-to-merchant-payments | Skill | 812 | 2d ago | Apache-2.0 | A | 184 | Claude Code |
| stripeCraftOS-dev/CraftBot | Skill | 402 | 2d ago | MIT | A | 79 | Claude Code, Codex |
| ai-slopwaybarrios/opencode-power-pack | Skill | 551 | 5d ago | MIT | A | 61 | Claude Code |
| stripemagnus919/agent-skills | Skill | 166 | 2d ago | MIT | A | 116 | Claude Code, Codex |
| asc-ppp-pricinghanamizuki/solopreneur | Skill | 156 | 3d ago | MIT | A | 45 | Claude Code |