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-production-triagegit 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-production-triage)<a href="https://agentmods.dev/skills/salesforcecommercecloud/b2c-developer-tooling/b2c-production-triage"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/b2c-production-triage/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-production-triage"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/b2c-production-triage.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 | $0.00058 | $0.01499 |
| Opus 5.5 | $0.00023 | $0.00600 |
| Sonnet 5.5 | $0.00012 | $0.00300 |
| Haiku 4.5 | $0.00006 | $0.00150 |
Grade A, and why
b2c-production-triage 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 20d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Production triage
Connect the toolkit's logs, job executions, business data, and configuration into an evidence-backed assessment and next action. Investigation does not authorize remediation. Use the symptom routes below rather than collecting every available signal.
Scope and impact
- Resolve the task's project/instance with
config_inspect; CLI:b2c setup inspect. Preserve the resolved target across calls. Ask for missing site, time window, timezone, symptom, or expected behavior; never invent IDs or silently switch tenants. - Start with the reported interval; if unspecified, propose the last two hours and label that assumption. Use fixed UTC boundaries for comparisons and paging.
- Record current impact (sites, checkout availability, order/data integrity, workaround) and the incident owner. Apply the team's severity policy; do not invent a priority or support SLA. Escalate active material impact early without waiting for root cause; agree who communicates and the next update time.
Access and tools
- Establish access: MCP, terminal/CLI, logs, data, source. Operator work does not
require a cartridge checkout. Credentials/setup issues: MCP
mcp/b2c-mcp-configsectionsetup-and-access; nativeb2c-config/b2c-auth, or the authentication guide (b2c docs read guide-authentication).
Prefer dedicated MCP tools; discover available names once. Read
skill://mcp/b2c-mcp-scapi/SKILL.md before using scapi_search/scapi_execute, as those
tools require. Read only the matching runbook/reference, not every linked skill.
Native assistants use the installed skill name; MCP can read these URIs or use
skills_read with collection: "b2c-ops" and a task query.
| Symptom | Toolkit path | Decision / detail |
|---|---|---|
| Error spike or integration errors | logs_list_files -> returned prefix -> logs_get_recent with count: 20, since, and a relevant search |
Defaults cover error/customerror, not every custom-* integration log. CLI: b2c logs list / b2c logs get. |
| Failed job or stale data | Code mode codemode.describe("builtin/failed-job-triage"), then run with fixed from/to -> execution IDs and logFilePath -> log tools |
Job health covers continuation, step details, exact WebDAV logs, and green-but-incomplete runs. |
| Checkout failures or orders down | Custom logs -> determine whether failures produce order records -> relevant data/traffic evidence | Checkout triage distinguishes checkout symptoms from failed-order records. |
| Find/count FAILED orders or investigate affected products | Verify Admin filter support; otherwise external OCAPI Shop order search -> safe IDs -> logs and selected Admin product reads | Failed-order triage owns enumeration, count/sample limits, and the workaround. No OCAPI helper exists inside code mode. |
| Bot, scraper or abusive traffic; edge 403/429 spikes | Zone protections and available edge traffic evidence via code mode cdn/zones/v1 |
Edge traffic triage classifies sources, checks owners, and finds protection gaps before any rule change. |
| Suspected code change | Code mode builtin/code-version-inspect: active/rollback versions and activation/modification timestamps |
Current metadata is not a complete activation history. Corroborate with release records. |
| Runtime-only defect | MCP debugger on an authorized reproduction target | Operator handoff is valid without source access. Do not halt production requests for routine triage. |
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.
- 20d ago Changed · +1 lines 0e8a30ab3c2b
- 25d ago Changed f2dd75959557
- 1mo ago Changed · -1 lines f52fe413a8f5
- 1mo ago First seen · 89 lines · 58 tokens per session scan A 168a02f87c21
b2c-production-triage is a skill published in the GitHub repository SalesforceCommerceCloud/b2c-developer-tooling (57 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 1,499 once invoked, about $0.0002 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 2026-09-12.
Other skills, from other repositories
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
feedback
Skill "feedback" from Hmbown/Codewhale, covering feedback, when to use, setup, workflow and non-goals.
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
atmos-schemas
JSON Schema for Atmos: stack-manifest and atmos.yaml config schemas, IDE auto-completion, validate stacks/schema/config, SchemaStore integration.
confirm-failures-are-causally-linked-to-the-task-before-reportin
When delegating a task affected by this skill, include.