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 SalesforceCommerceCloud/b2c-developer-tooling --skill b2c-scapi-admingit clone --depth 1 https://github.com/SalesforceCommerceCloud/b2c-developer-toolingWrote 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/salesforcecommercecloud/b2c-developer-tooling/b2c-scapi-admin)<a href="https://agentmods.dev/skills/salesforcecommercecloud/b2c-developer-tooling/b2c-scapi-admin"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/b2c-scapi-admin/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/salesforcecommercecloud/b2c-developer-tooling/b2c-scapi-admin"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/b2c-scapi-admin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 17 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 124 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Data Exfiltration · line 72 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Agent Snooping · line 74 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 455 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Server-Side Request Forgery · line 138 Request target host is built from a dynamic or untrusted value. If the host is attacker-influenced, this enables SSRF to arbitrary internal or metadata endpoints.Fix: Do not build request URLs from untrusted input. Validate the host against an allowlist and reject internal/metadata addresses before issuing the request.
- medium Server-Side Request Forgery · line 146 Request target host is built from a dynamic or untrusted value. If the host is attacker-influenced, this enables SSRF to arbitrary internal or metadata endpoints.Fix: Do not build request URLs from untrusted input. Validate the host against an allowlist and reject internal/metadata addresses before issuing the request.
- medium Server-Side Request Forgery · line 172 Request target host is built from a dynamic or untrusted value. If the host is attacker-influenced, this enables SSRF to arbitrary internal or metadata endpoints.Fix: Do not build request URLs from untrusted input. Validate the host against an allowlist and reject internal/metadata addresses before issuing the request.
- medium Server-Side Request Forgery · line 180 Request target host is built from a dynamic or untrusted value. If the host is attacker-influenced, this enables SSRF to arbitrary internal or metadata endpoints.Fix: Do not build request URLs from untrusted input. Validate the host against an allowlist and reject internal/metadata addresses before issuing the request.
- medium Server-Side Request Forgery · line 198 Request target host is built from a dynamic or untrusted value. If the host is attacker-influenced, this enables SSRF to arbitrary internal or metadata endpoints.Fix: Do not build request URLs from untrusted input. Validate the host against an allowlist and reject internal/metadata addresses before issuing the request.
- medium Server-Side Request Forgery · line 206 Request target host is built from a dynamic or untrusted value. If the host is attacker-influenced, this enables SSRF to arbitrary internal or metadata endpoints.Fix: Do not build request URLs from untrusted input. Validate the host against an allowlist and reject internal/metadata addresses before issuing the request.
- medium Server-Side Request Forgery · line 232 Request target host is built from a dynamic or untrusted value. If the host is attacker-influenced, this enables SSRF to arbitrary internal or metadata endpoints.Fix: Do not build request URLs from untrusted input. Validate the host against an allowlist and reject internal/metadata addresses before issuing the request.
- medium Server-Side Request Forgery · line 248 Request target host is built from a dynamic or untrusted value. If the host is attacker-influenced, this enables SSRF to arbitrary internal or metadata endpoints.Fix: Do not build request URLs from untrusted input. Validate the host against an allowlist and reject internal/metadata addresses before issuing the request.
- medium Server-Side Request Forgery · line 287 Request target host is built from a dynamic or untrusted value. If the host is attacker-influenced, this enables SSRF to arbitrary internal or metadata endpoints.Fix: Do not build request URLs from untrusted input. Validate the host against an allowlist and reject internal/metadata addresses before issuing the request.
- medium Server-Side Request Forgery · line 335 Request target host is built from a dynamic or untrusted value. If the host is attacker-influenced, this enables SSRF to arbitrary internal or metadata endpoints.Fix: Do not build request URLs from untrusted input. Validate the host against an allowlist and reject internal/metadata addresses before issuing the request.
- medium Server-Side Request Forgery · line 362 Request target host is built from a dynamic or untrusted value. If the host is attacker-influenced, this enables SSRF to arbitrary internal or metadata endpoints.Fix: Do not build request URLs from untrusted input. Validate the host against an allowlist and reject internal/metadata addresses before issuing the request.
- medium Server-Side Request Forgery · line 370 Request target host is built from a dynamic or untrusted value. If the host is attacker-influenced, this enables SSRF to arbitrary internal or metadata endpoints.Fix: Do not build request URLs from untrusted input. Validate the host against an allowlist and reject internal/metadata addresses before issuing the request.
- medium Agent Snooping · line 457 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00142 | $0.00772 |
| Opus 5.5 | $0.00057 | $0.00309 |
| Sonnet 5.5 | $0.00028 | $0.00154 |
| Haiku 4.5 | $0.00014 | $0.00077 |
Grade A, and why
b2c-scapi-admin 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 21d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SCAPI Admin APIs
Build backend integrations or manage Commerce data through standard Admin APIs.
Use the b2c-scapi-shopper skill for storefront flows.
Tool choice
When B2C MCP is available:
- Prefer a dedicated task tool. Otherwise read
skill://mcp/b2c-mcp-scapi/SKILL.mdonce through resources orskills_read, then useskillRead: true. scapi_search: bundled standard contracts, offline. Find method/path/operationId, then inspect selected parameters, fields, and security scopes. Return compact projections.scapi_execute: supported Admin JSON operations with configured Account Manager auth and automatic operation/tenant scopes. Useconfig_inspectwith masking; do not fetch or print tokens manually for these calls.scapi_schemas_list: live tenant schemas, including custom attributes and APIs.scapi_custom_apis_get_status: custom registration. Custom execution and binary transfers are unsupported by code mode; use an appropriate integration client.docs_search/docs_read: platform semantics, limits, and auth setup. No duplicate docs lookup is needed merely to repeat a discovered contract.
For CLI/integration development: b2c scapi schemas list and
b2c scapi schemas get <family> <name> <version> retrieve live contracts.
Read integration examples only when implementing
an external client, token flow, or bulk import. There is no CLI code-mode equivalent.
Execute deliberately
- Use configured short code, tenant, and site values. Admin auth requires an
Account Manager client, API grants, and
SALESFORCE_COMMERCE_API:<tenant_id>. SLAS credentials do not replace Admin credentials. - Inspect the operation before use; examples are illustrative. For tenant-specific fields use live schemas. Check official docs for version-specific semantics.
- Distinguish creation from update; PUT may do both. Verify existence and intent, then read back meaningful fields. Check earlier writes before retrying a failure.
- Page/filter at the API and return IDs, selected fields, totals/hasMore, and errors. Do not emit whole response trees or log credentials.
- Safety is method-based: POST searches can require a targeted allow rule. Confirmation-required code-mode requests stop; do not bypass them.
What ships with it
4 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.
- 21d ago Changed 4cc116af0628
- 1mo ago Changed · -409 lines 7242ea39682e
- 1mo ago First seen · 463 lines · 142 tokens per session scan A b05bc732e6de
b2c-scapi-admin is a skill published in the GitHub repository SalesforceCommerceCloud/b2c-developer-tooling (56 stars, last pushed today), licensed Apache-2.0. It adds 142 tokens to every session and 772 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
shopify-app-development
Build embedded Shopify apps using the Remix framework, App Bridge for UI integration, Polaris components, and OAuth authentication flow.
sfcc-ocapi-scapi
Integrate with Salesforce Commerce Cloud's headless APIs (OCAPI and Shopper APIs) to build custom storefronts and mobile commerce experiences.
grow-payment-gateway
Integrate Grow by Meshulam payment gateway into Israeli applications -- covers payment pages (iframe/redirect/SDK), tokenization, recurring billing, payment links, refunds, invoices, webhooks, and 3DS authentication via the Grow Light API. Use when user asks to accept payments via Grow or Meshulam, set up "slikat…
israeli-shipping-manager
Build and manage shipping integrations with Israeli carriers, including Israel Post, Cheetah, HFD, Mahir Li, GetPackage, and UPS Israel, plus locker pickup services (BOX2GO, Shlager, Done, UPS lockers). Use when user asks about "shipping Israel", "Cheetah delivery", "meshloach", "shipping label", "HFD", "locker pickup…
convex-billing
Add Stripe billing/payments to the Convex app via @convex-dev/stripe (checkout + webhook + gating).
wikipedia
Search and read Wikipedia via x wkp — MediaWiki API, no API key, zero install; query, extract, suggest, and DDG route in one module. Load for wiki, wikipedia, encyclopedia lookup, article summary.