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-docsgit 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-docs)<a href="https://agentmods.dev/skills/salesforcecommercecloud/b2c-developer-tooling/b2c-docs"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/b2c-docs/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-docs"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/b2c-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to medium
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 →
- medium MCP Rug Pull · line 12 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Prompt Injection · line 230 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 234 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 235 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 236 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 237 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 239 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00170 | $0.04219 |
| Opus 5.5 | $0.00068 | $0.01688 |
| Sonnet 5.5 | $0.00034 | $0.00844 |
| Haiku 4.5 | $0.00017 | $0.00422 |
Grade A, and why
b2c-docs 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 14d 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
B2C Docs Skill
Use this skill for ANY B2C Commerce developer or administrator question that is not already grounded in a loaded skill or the current project context. The docs corpus covers Script API reference, Commerce API (SCAPI/OCAPI) integration patterns, storefront framework guides (SFRA, PWA Kit, Storefront Next), Business Manager administration and merchandising (Salesforce Help), job step parameters, authentication flows, and tooling configuration.
Use the b2c CLI to search and read B2C Commerce documentation spanning multiple corpora: Script API reference (dw.* classes/modules), Developer Center guides (conceptual and how-to content across Commerce API, PWA Kit, SFRA, and more), Salesforce Help (Business Manager administration and merchandising content from help.salesforce.com), tooling documentation (this project's own guides), the standard (system) job step catalog, and XSD schemas.
Tip: If
b2cis not installed globally, usenpx @salesforce/b2c-cliinstead (e.g.,npx @salesforce/b2c-cli docs search ProductMgr).
MCP parity: If the
b2c-dx-mcpserver is connected, its docs tools —docs_search,docs_read,docs_list,docs_schema_search,docs_schema_read, anddocs_schema_list— cover the same corpus with the same search, workspace-awareness, and topic-scoping behavior described here.
Key Features
- Multi-corpus search — Search across Script API, Developer Center guides, OCAPI reference, Salesforce Help (admin + merchandising), internal tooling docs (guides, CLI reference, MCP, and VS Code extension), job steps, and schemas in a unified index
- Workspace-aware search — Auto-detects project type (cartridges, SFRA, PWA Kit, Storefront Next) and boosts relevant documentation while de-boosting competing storefront frameworks
- Category filtering — Use
--categoryto narrow results to a specific corpus (e.g.,commerce-api,pwa-kit-managed-runtime,sfra,script-api,help-admin,help-merchant,help-kb) - Triage metadata — Search results include
category,summary,keywords, andurlto help identify the right match without reading full content - Online content with local cache — Script API, Developer Center guides, and Salesforce Help are fetched online when you read them and cached locally (memory + on-disk, 7-day TTL) so repeat reads avoid the network; graceful offline fallback shows the summary + headings + both URLs
- Content-aware ranking — BM25-style search indexes titles, section headings, summaries, and keywords for better recall on conceptual questions
- Dual URLs — Every publicly-available doc entry carries both
url(human-facing .html page) andsourceUrl(raw .md source). Script API entries link developer.salesforce.com; Salesforce Help entries link the live help.salesforce.com article while content is served from a raw markdown mirror. Content is fetched via sourceUrl with offline fallback - Related content — Developer Center guides include their immediate TOC parent and children as
relatedEntries; Salesforce Help landing entries use the same field for linked child articles and include a matching Related Content section in their raw Markdown - Topic allowlist — Bound the entire corpus to chosen categories via
--topicsflag orSFCC_DOCS_TOPICSenv var, or thedocsCategoriesconfig field (dw.jsondocs-categories,SFCC_DOCS_CATEGORIES, package.json). The MCP server has a--docs-topicsstartup flag - Payload-conscious defaults — MCP tools limit result count (5) and return lean fields by default; CLI defaults to 20 results; verbose mode adds extended fields
What ships with it
1 file 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.
- 14d ago Changed · +20 lines 02ff9c72c4f9
- 17d ago Changed · +1 lines · +3 tokens per session eccffd2046a0
- 20d ago Changed · +1 lines · +3 tokens per session 80a067330a06
- 21d ago Changed · +5 lines dacd01a05a8d
- 1mo ago First seen · 275 lines · 164 tokens per session scan A d8cd0c1ed73c
b2c-docs is a skill published in the GitHub repository SalesforceCommerceCloud/b2c-developer-tooling (56 stars, last pushed today), licensed Apache-2.0. It adds 170 tokens to every session and 4,219 once invoked, about $0.0007 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
gws-classroom
Google Classroom: Manage classes, rosters, and coursework.
get-rep-call-feedback
Use when the user wants evidence-backed coaching for one rep's calls, especially by comparing the rep with peer examples to identify repeatable best practices, specific upgrade moments, and practical next-call language.
tutorial
Interactive tutorial teaching Ouroboros hands-on.
recipe-create-classroom-course
Create a Google Classroom course and invite students.
socratic-quiz
Use this when the user wants to deeply understand something through guided questioning. Trigger phrases include: "quiz me", "help me understand", "Socratic", "teach me", "walk me through with questions", "test my understanding", or when the user asks for an explanation and would benefit more from guided discovery than…
daiso-cli
A command-line interface for searching Daiso and related Korean shopping, store, food, cinema, and convenience-store data through the Daiso project. It can return structured JSON for searches and comparisons.