Agent Skills: research-precedent

  <substep n="1a" title="Track Progress">
    <action if="first iteration">Create todo list from all instruction step titles (TodoWrite)</action>
    <action>Mark current step as in_progress (TodoWrite)</action>
  </substep>

  <substep n="1b" title="Handle Step Attributes">
    <check>If optional="true" and NOT YOLO -> Use Question tool to ask user whether to include (Yes/Skip)</check>
    <check>If if="condition" -> Evaluate condition</check>
    <check>If for-each="item" -> Repeat step for each item</check>
    <check>If repeat="n" -> Repeat step n times</check>
  </substep>

  <substep n="1c" title="Execute Step Content">
    <action>Process step instructions (markdown or XML tags)</action>
    <action>Replace {{variables}} with values (ask user if unknown)</action>
    <execute-tags>
      <tag>action -> Perform the action</tag>
      <tag>action type="script" -> Execute as shell command, capture output</tag>
      <tag>check if="condition" -> Conditional block wrapping actions (requires closing &lt;/check&gt;)</tag>
      <tag>ask -> Prompt user using Question tool and WAIT for response. When options exist, present them as selectable choices. For open-ended questions, provide helpful suggested options with custom input enabled</tag>
      <tag>invoke-skill name="skill-name" -> Execute another skill via OpenCode skill system</tag>
      <tag>invoke-agent name="subagent" prompt="task" -> Delegate to subagent via Task tool</tag>
      <tag>goto step="x" -> Jump to specified step (used for explicit loop-back in Q-R style flows)</tag>
    </execute-tags>
  </substep>

  <substep n="1d" title="Handle template-output Tags">
    <if tag="template-output">
      <mandate>Generate content for this section</mandate>
      <mandate>Save to file (Write first time, Edit subsequent)</mandate>
      <action>Display generated content</action>
      <action>Use Question tool to present checkpoint options. WAIT for response.
        <options>
          <option label="Continue" description="Approve this section and move to the next step" />
          <option label="Advanced Elicitation" description="Explore this section deeper before proceeding" />
          <option label="YOLO" description="Auto-complete the rest of this workflow without stopping" />
        </options>
        <if response="Advanced Elicitation">
          <action>Invoke advanced-elicitation skill</action>
        </if>
        <if response="Continue">
          <action>Continue to next step</action>
        </if>
        <if response="YOLO">
          <action>Enter YOLO mode for the rest of the workflow</action>
        </if>
      </action>
    </if>
  </substep>

  <substep n="1e" title="Step Completion">
    <action>Mark current step as completed (TodoWrite)</action>
    <check>If no special tags and NOT YOLO:</check>
    <action>Use Question tool to ask:
      <options>
        <option label="Continue" description="Proceed to the next step" />
        <option label="Edit" description="Revise this step before moving on" />
      </options>
    </action>
  </substep>
</step>

<step n="2" title="Completion">
  <check>Confirm all instruction steps have been executed</check>
  <output>Workflow complete.</output>
</step>

<inputs>
  Interactive (user invokes [PR]):
  - What we are seeking precedent FOR (the problem or pattern);
    mentioned sources read first.

  Autonomous (dispatched from a workflow):
  - precedent_for (required): the problem, pattern, or capability we
    are seeking prior art on
  - scope (optional): where to look (internal globs, domains)
  - web_search_approved (boolean): required true to hunt external
    precedent via web-search-researcher
  - output_location (optional): override for the research directory
</inputs>

<outputs>
  A precedent register persisted to the thoughts research directory:
  per-precedent entries with source citation, what-matches,
  what-differs, and a transfer-fit class; plus recommended Scout
  follow-ups for external projects worth deep study. "No precedent
  found" is a valid register. Autonomous mode returns a structured
  signal carrying the register path.
</outputs>

<key-discipline>
  Applicability is factual, not a recommendation. State what matches
  and what differs with evidence, and classify transfer-fit. Do NOT
  say "we should adopt this" — whether to adopt is the orchestrator's
  call. The transfer-fit class is evidence-grading, like a confidence
  level, not an action.

  No precedent is a finding: "hunted internal + thoughts + web; no
  prior art" tells the caller the work is greenfield. Ship it as a
  cited register, not as a failure.

  PR hunts; it does not clone. External precedent is found at
  web-discovery depth. When a project warrants deep code study,
  recommend Scout External Codebase rather than cloning here.

  Hide-the-intent: every child prompt carries the hunt question
  alone — never the parent task's intent.
</key-discipline>

<step n="1" title="Orient and Plan the Hunt">
  <action>Load and execute: references/steps/step-01-orient-plan-hunt.xml</action>
</step>

<step n="2" title="Dispatch Hunts">
  <action>Load and execute: references/steps/step-02-dispatch-hunts.xml</action>
</step>

<step n="3" title="Assess Applicability and Synthesize Register">
  <action>Load and execute: references/steps/step-03-assess-synthesize.xml</action>
</step>

<step n="4" title="Persist">
  <action>Load and execute: references/steps/step-04-persist.xml</action>
</step>

<step n="5" title="Return">
  <action>Load and execute: references/steps/step-05-return.xml</action>
</step>