Workflow Triggering

What it does

When your agent uses it

• Starting workflows manually via the Timeline UI
• Programmatically via WorkflowSession.startWorkflow()
• Via the HTTP Workflow API
• Through Manage Publication

Example prompts

• “/workflow-triggering”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Manual via Timeline UI
2. 2Manage Publication (Multi-Page)
3. 3Programmatic (WorkflowSession API)
4. 4HTTP Workflow API
5. 5Replication-Linked Trigger (6.5 LTS Only)

What it can do on your machine

Read from SKILL.md and the folder at commit 985c436. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Workflow Triggering loads about 1.4k tokens when it runs, and up to ~7.7k if it reads all its reference files. Until then it costs about 90 tokens; SKILL.md has 343 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~90

When it runs · the whole SKILL.md, loaded when a task matches

~1.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~7.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from adobe/skills at commit 985c436, republished under its Apache-2.0 licence (© adobe). 343 words, ~1,432 tokens.

name

workflow-triggering

description

Start AEM Workflows on AEM 6.5 LTS using all available triggering mechanisms. Use when starting workflows manually via the Timeline UI, programmatically via WorkflowSession.startWorkflow(), via the HTTP Workflow API, through Manage Publication, through replication triggers, or passing initial metadata and payload to a workflow instance.

license

Apache-2.0

@Component(service = WorkflowStarterService.class)
public class WorkflowStarterService {

    @Reference
    private ResourceResolverFactory resolverFactory;

    public String startWorkflow(String payloadPath, String modelId) throws Exception {
        Map<String, Object> auth = Collections.singletonMap(
            ResourceResolverFactory.SUBSERVICE, "workflow-starter");
        try (ResourceResolver resolver = resolverFactory.getServiceResourceResolver(auth)) {
            WorkflowSession wfSession = resolver.adaptTo(WorkflowSession.class);
            WorkflowModel model = wfSession.getModel(modelId);
            WorkflowData data = wfSession.newWorkflowData("JCR_PATH", payloadPath);
            data.getMetaDataMap().put("workflowTitle", "Triggered by batch job");

            Workflow instance = wfSession.startWorkflow(model, data);
            return instance.getId();
        }
    }
}

# Start — returns HTTP 201 with an HTML body linking to the new instance path
curl -u admin:admin -X POST \
  "http://localhost:4502/var/workflow/instances" \
  --data-urlencode "_charset_=utf-8" \
  --data-urlencode "model=/var/workflow/models/my-workflow" \
  --data-urlencode "payloadType=JCR_PATH" \
  --data-urlencode "payload=/content/my-site/en/home" \
  --data-urlencode "workflowTitle=My Test Run" \
  --data-urlencode "startComment=triggered via HTTP API"

# List instances — filter by state with a selector (.RUNNING.json, .COMPLETED.json, ...)
curl -u admin:admin "http://localhost:4502/var/workflow/instances.json"
curl -u admin:admin "http://localhost:4502/var/workflow/instances.RUNNING.json"

# Instance detail — the id is the path returned at start,
# e.g. /var/workflow/instances/server0/<date>/my-workflow_1
curl -u admin:admin \
  "http://localhost:4502/var/workflow/instances/server0/<date>/my-workflow_1.json"

# Terminate (abort) — POST state=ABORTED to the instance path, returns HTTP 200
curl -u admin:admin -X POST \
  "http://localhost:4502/var/workflow/instances/server0/<date>/my-workflow_1" \
  --data-urlencode "_charset_=utf-8" \
  --data-urlencode "state=ABORTED" \
  --data-urlencode "terminateComment=cleanup"

© adobe, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (references) in plugins/aem/6.5-lts/skills/aem-workflow/workflow-triggering of adobe/skills.

• SKILL.md
• references/workflow-foundation/65-lts-guardrails.md
• references/workflow-foundation/README.md
• references/workflow-foundation/api-reference.md
• references/workflow-foundation/architecture-overview.md
• references/workflow-foundation/jcr-paths-reference.md
• references/workflow-foundation/quick-start-guide.md
• references/workflow-triggering/programmatic-api.md
• references/workflow-triggering/triggering-mechanisms.md

Open the folder on GitHubat commit 985c436