Mandatory first-turn startup procedure — checks for existing engagements, resume/new selection, workspace initialization.
60
70%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./packages/decepticon/decepticon/skills/standard/decepticon/engagement-startup/SKILL.mdExecute this procedure on every session start, before any other action.
The launcher normally injects the workspace root. Use that exact root when it is
present in the engagement context; otherwise use /workspace.
Before calling read_file, write_file, edit_file, ls, glob, or grep,
call:
load_opplan(workspace_path="<active workspace root>")This call has two outcomes:
plan/opplan.json: objectives and engagement metadata are loaded.plan/opplan.json: the workspace is still bound so planning files
can be created. This is the expected new-engagement path, not a fatal error.Do not probe the filesystem before this call.
Read the active workspace's planning documents:
read_file("<active workspace root>/plan/roe.json")
read_file("<active workspace root>/plan/conops.json")
read_file("<active workspace root>/plan/deconfliction.json")If any document is missing, delegate to Soundwave:
task("soundwave", "Workspace: <active workspace root>. Regenerate the missing planning documents.")The launcher already selected the engagement. Do not enumerate the shared
/workspace root, invent another workspace directory, or ask the operator to
select the engagement again.
When load_opplan loaded objectives:
findings/.When no OPPLAN exists but the planning documents are present:
add_objective.bash from this workflow.enumerate_skills,
save_opplan, or other aliases.0cf691e
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.