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-job-healthgit 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-job-health)<a href="https://agentmods.dev/skills/salesforcecommercecloud/b2c-developer-tooling/b2c-job-health"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/b2c-job-health/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-job-health"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/b2c-job-health.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 | $0.00045 | $0.00986 |
| Opus 5 | $0.00023 | $0.00493 |
| Sonnet 5 | $0.00009 | $0.00197 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
b2c-job-health 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 yesterday.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job health
Outcome: identify which scheduled work completed its business purpose, what is late/failed/partial, and whether intervention or a developer handoff is needed.
Scope and impact
Resolve instance/site and a fixed UTC interval with config_inspect (CLI:
b2c setup inspect). Obtain the expected jobs, schedule/timezone, and intended
updates from the user or available configuration. No matching execution is
"missing" only when a run was actually expected.
Record the business deadline, affected data/sites, and owner. For material impact,
use the team's incident severity/update process; a routine review need not declare
an incident. Do not invent impact from a red status alone.
Access and tools
| Evidence | Preferred MCP path | CLI fallback |
|---|---|---|
| Execution history and steps | SCAPI Jobs through code mode | b2c job search; check --help for filters |
| Known execution log | logs_list_files / logs_get_recent with its relative log path |
b2c job log JOB_ID EXECUTION_ID |
| Expected product/data change | Discover the relevant Admin operation and select affected fields | Relevant CLI/data workflow if supported |
| Code-version clues | Available deployment/history API, otherwise CLI | b2c code list; modification time is not activation history |
Read skill://mcp/scapi/SKILL.md before code mode. Use its search/discovery
contract; project/instance context belongs on tool calls. Authentication is
managed. Do not export tokens or use ambient fetch inside code mode.
Checks and decisions
- Search a small page of executions in the interval. For routine review, include successful and unfinished runs, not only failures. Compare against the expected schedule; inspect relevant steps/duration and time zone before calling a run late.
- For failure-only review, reuse
builtin/failed-job-triage: inspect withcodemode.describe, thencodemode.runwith fixedfrom,to, andlimit(maximum 3). Continue using its returned offset/window only as needed. Keep errors and partial results. The snippet returns selected execution fields, notstepExecutions; fetch the selected execution's detail if steps matter. A POST search can be blocked by Safety Mode; explain the denied read operation rather than weakening policy. - Read the log for the selected execution. Use its returned
logFilePath; for nested paths remove only an initialLogs/for MCPprefixes. Top-level files need their discovered category prefix, not the filename. For a nested directory use a trailing slash. Discover matching files, then request bounded entries around the failure. Defaults only search error/customerror. See job-log details if the result is empty or incomplete. - Identify the first relevant fault, processed/skipped records, and which steps actually ran. Job transitions can continue after errors; do not assume every later step was skipped. Green status can also hide skipped or incomplete work.
- Verify a small sample of the expected data and one healthy comparison. Correlate changes without claiming causation from matching timestamps alone.
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.
- yesterday First seen · 77 lines · 45 tokens per session scan A c71d33ef38d8
b2c-job-health is a skill published in the GitHub repository SalesforceCommerceCloud/b2c-developer-tooling (53 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 986 once invoked, about $0.0002 per session on Opus 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.
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
dd-triage-flaky-test
Load when investigating a specific flaky test. Gets history, failure pattern, and category, then recommends fix, quarantine, or escalate.
atmos-schemas
JSON Schema for Atmos: stack-manifest and atmos.yaml config schemas, IDE auto-completion, validate stacks/schema/config, SchemaStore integration.
dd-symdb
Symbol Database - search service symbols, find probe-able methods.