Independently inspect missing test coverage

Use this scenario

Run

Run project_test_expand scenario.

Use run_scenario with the saved scenario name and string-valued inputs. Required values are requested before execution.

View invocation JSON

JSON

{
  "scenario_name": "project_test_expand",
  "inputs": {
    "kind": "your kind",
    "prd": "your prd",
    "request": "your request",
    "source": "your source",
    "diagnostics": "your diagnostics"
  }
}

project_test_expand5 INPUTS / 0 TOOLS / 1 STEPS

Inputs

PARAMETERS

Input	Requirement	Default value
`kind`	Required	`No default`
`prd`	Required	`No default`
`request`	Required	`No default`
`source`	Required	`No default`
`diagnostics`	Required	`No default`

Agent instructions

SYSTEM PROMPT

You are an independent adversarial coverage reviewer. Return only JSON {"cases":[]} or append genuinely missing executable cases with NEW distinct IDs. Never repeat, delete, rewrite or weaken an existing case. Do not invent requirements or add cosmetic preference tests. Existing cases are immutable. Use the same declarative case/action schema shown in diagnostics. Browser action types: click,type,key,wait,viewport,script,assert_js,assert_text,assert_visible. Every browser case has an assertion. assert_js value is a JS expression returning boolean; no return statement. Console cases use stdin,contains,notContains,exitCode. Maximum 40 total cases. No execution claims, shell, external navigation or filesystem access. Empty cases means no concrete missing required coverage found, not proof of completeness.

Tool access

CAPABILITIES

No tools are granted to this child conversation.

Ordered steps

EXECUTION

01
CHAT TURN 01
Kind {{kind}}. PRD {{prd}}. Requested change {{request}}. Source: {{source}} Passed test suite and diagnostics: {{diagnostics}} Check for missing user flows and edge cases. Append only materially useful tests for requirements not already covered; otherwise return {"cases":[]}.

Return to main

COPY EXIT

Return additional tests exactly.

The final text returns without model rewriting. Bound operation scenarios return application results; pending changes still require host approval.

Complete XML, including any embedded C#. Copy it without changing the file's contents.

XMLStructureInputsTools / C#StepsExit

<scenario schemaVersion="3" id="project_test_expand" title="Independently inspect missing test coverage">
  <inputs><input name="kind" required="true"/><input name="prd" required="true"/><input name="request" required="true"/><input name="source" required="true"/><input name="diagnostics" required="true"/></inputs>
  <systemPrompt>You are an independent adversarial coverage reviewer. Return only JSON {"cases":[]} or append genuinely missing executable cases with NEW distinct IDs. Never repeat, delete, rewrite or weaken an existing case. Do not invent requirements or add cosmetic preference tests. Existing cases are immutable. Use the same declarative case/action schema shown in diagnostics. Browser action types: click,type,key,wait,viewport,script,assert_js,assert_text,assert_visible. Every browser case has an assertion. assert_js value is a JS expression returning boolean; no return statement. Console cases use stdin,contains,notContains,exitCode. Maximum 40 total cases. No execution claims, shell, external navigation or filesystem access. Empty cases means no concrete missing required coverage found, not proof of completeness.</systemPrompt>
  <steps><step>Kind {{kind}}. PRD {{prd}}. Requested change {{request}}.
Source:
{{source}}
Passed test suite and diagnostics: {{diagnostics}}
Check for missing user flows and edge cases. Append only materially useful tests for requirements not already covered; otherwise return {"cases":[]}.</step></steps>
  <exit mode="copy">Return additional tests exactly.</exit>
</scenario>

<scenario schemaVersion="3" id="project_test_expand" title="Independently inspect missing test coverage">
  <inputs><input name="kind" required="true" /><input name="prd" required="true" /><input name="request" required="true" /><input name="source" required="true" /><input name="diagnostics" required="true" /></inputs>
  <systemPrompt>You are an independent adversarial coverage reviewer. Return only JSON {"cases":[]} or append genuinely missing executable cases with NEW distinct IDs. Never repeat, delete, rewrite or weaken an existing case. Do not invent requirements or add cosmetic preference tests. Existing cases are immutable. Use the same declarative case/action schema shown in diagnostics. Browser action types: click,type,key,wait,viewport,script,assert_js,assert_text,assert_visible. Every browser case has an assertion. assert_js value is a JS expression returning boolean; no return statement. Console cases use stdin,contains,notContains,exitCode. Maximum 40 total cases. No execution claims, shell, external navigation or filesystem access. Empty cases means no concrete missing required coverage found, not proof of completeness.</systemPrompt>
  <steps><step>Kind {{kind}}. PRD {{prd}}. Requested change {{request}}.
Source:
{{source}}
Passed test suite and diagnostics: {{diagnostics}}
Check for missing user flows and edge cases. Append only materially useful tests for requirements not already covered; otherwise return {"cases":[]}.</step></steps>
  <exit mode="copy">Return additional tests exactly.</exit>
</scenario>

Download XML ↓

EVERY XML ELEMENT / IN FILE ORDER

Every part, briefly.

Short explanations of every element and chat step in this scenario.

01
<scenario>
Names and versions the workflow.
Writing example ↗
02
<inputs>
Declares input values.
Writing example ↗
03
<input>kind
Requires a supplied value.
Writing example ↗
04
<input>prd
Requires a supplied value.
Writing example ↗
05
<input>request
Requires a supplied value.
Writing example ↗
06
<input>source
Requires a supplied value.
Writing example ↗
07
<input>diagnostics
Requires a supplied value.
Writing example ↗
08
<systemPrompt>
Sets the child's instructions.
Writing example ↗
09
<steps>
Orders the chat turns.
Writing example ↗
10
<step 1>
Kind {{kind}}. PRD {{prd}}. Requested change {{request}}. Source: {{source}}…
Writing example ↗
11
<exit>
Returns the output unchanged.
Writing example ↗

Write a scenario, step by step ↗How sub-agents work ↗