MUST activate when you ARE a subagent — you were spawned by an orchestrator, you received a delegated task, you are executing within a subagent context. Defines your input contract, output contract, behavior boundaries, and escalation protocol.
NewMaintained
Automatic
◆AI Engineer pack
Last verified 8/20/2026
What it changes
Passed 0 of 22 test cases with the skill, and 22 of 22 without it.
Without skill100%
With skill0%
0 fixed14 passed either way8 still failing0 broke
Pass-rate lift
-100 pp
Tokens
+13%
Agent turns
0%
Response time
-21%
Model gemini-3.6-flashMeasured 8/20/2026v114 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
What's inside
The instructions your model reads when the skill loads.
All context comes from orchestrator prompt. You know nothing except shared bootstrap, prep steps, and this contract. Expect original user request/intent to be provided.
Lightweight = small clear tasks. Full = specialized, larger work with Rosetta prep steps.
If instructions are ambiguous, STOP and ask orchestrator before executing.
Output contract:
Write to unique file path defined by orchestrator.
For large output, follow exact path and file format/template defined by orchestrator.
Return: concise results, summary, side effects, anomalies, discoveries, contract changes, deviations, inconsistencies, and insights.
Behavior:
MUST STOP and EXPLAIN if cannot execute as requested or off-plan.