flowchart TD
    Start([Parse feature_request]) --> Q{Contains "GitHub Issue: #N"<br>or "Issue: #N" or "#N"?}
    Q -->|Yes — issue number found| List["Call artifact_list(issue_number=N)<br>to discover registered artifacts"]
    Q -->|No — no issue reference| Skip[Skip artifact discovery<br>Proceed normally]
    List --> Found{Artifacts returned?}
    Found -->|Yes| Store["Store artifact list as discovered_artifacts<br>Include paths and types in each<br>phase delegation prompt"]
    Found -->|No or empty| Skip
    Store --> Phase1([Proceed to Phase 1])
    Skip --> Phase1

<prior_artifacts>
The following artifacts are already registered for this issue. Read any relevant
ones via artifact_read(issue_number={issue}, artifact_type="{type}") before
starting your work — they contain prior research and analysis that should
inform your output.

{for each artifact: "- {artifact_type}: {path}"}
</prior_artifacts>

You are part of a team that is currently working on the {work_type} {feature_name}.
Read the details about the milestone and plan you are a part of at backlog_view(selector="#{issue}").

<quality_vigilance>
Your task among all other things you are doing is to be consistently striving for
product quality improvements and aligning with the design intent. If you see something
that seems misaligned, verify it, and then note your concerns and findings concisely
in your response in a <concerns></concerns> block. Point out duplication, contradictions,
statements of fact without citation, code smells, missing documentation.
</quality_vigilance>

You are part of a team that is currently working on the {work_type} {feature_name}.
Read the details about the milestone and plan you are a part of at backlog_view(selector="#{issue}").

<quality_vigilance>
Your task among all other things you are doing is to be consistently striving for
product quality improvements and aligning with the design intent. If you see something
that seems misaligned, verify it, and then note your concerns and findings concisely
in your response in a <concerns></concerns> block. Point out duplication, contradictions,
statements of fact without citation, code smells, missing documentation.
</quality_vigilance>

Research #{issue}: "{title}".
If research artifacts exist for this issue, read them via
artifact_read(issue_number={issue}, artifact_type="research") before starting
discovery — they contain prior investigation findings that should be incorporated.
Produce feature-context-{slug}.md content with WHAT/WHY analysis — problem space, desired
outcome, stakeholders, risks, open questions.
Return the full markdown content in your response. Do NOT write to disk.
Do NOT prescribe HOW to build it.
If the feature involves replacing or migrating a local module to an external tool,
you MUST perform a Replacement Coverage Analysis: enumerate all capabilities of the
local module, enumerate the replacement's capabilities, and produce a coverage matrix
(COVERED/PARTIAL/MISSING for each capability). Include the matrix in the feature-context
document. Surface any PARTIAL or MISSING capabilities as questions.

mcp__plugin_dh_backlog__artifact_register(
    issue_number={issue},
    artifact_type="feature-context",
    path="plan/feature-context-{slug}.md",  # state-relative path
    agent="feature-researcher"
)

You are part of a team that is currently working on the {work_type} {feature_name}.
Read the details about the milestone and plan you are a part of at backlog_view(selector="#{issue}").

<quality_vigilance>
Your task among all other things you are doing is to be consistently striving for
product quality improvements and aligning with the design intent. If you see something
that seems misaligned, verify it, and then note your concerns and findings concisely
in your response in a <concerns></concerns> block. Point out duplication, contradictions,
statements of fact without citation, code smells, missing documentation.
</quality_vigilance>

Analyze {focus_area} for #{issue}: "{title}".
Produce {focus_area}.md content documenting what exists today — patterns,
conventions, constraints.
Return the full markdown content in your response. Do NOT write to disk.
Do NOT prescribe changes.

mcp__plugin_dh_backlog__artifact_register(
    issue_number={issue},
    artifact_type="codebase-analysis",
    path="plan/codebase/{FOCUS}.md",  # state-relative path
    agent="codebase-analyzer"
)

flowchart TD
    Scan[Scan project root for language markers] --> Found{Marker found?}
    Found -->|pyproject.toml| Py[Search Python language manifest]
    Found -->|package.json| TS[Search TypeScript language manifest]
    Found -->|Cargo.toml| Rust[Search Rust language manifest]
    Found -->|None| FB[Fallback: general-purpose agent]
    Py --> ManifestFound{Manifest exists?}
    TS --> ManifestFound
    Rust --> ManifestFound
    ManifestFound -->|Yes| Resolve["Resolve design-spec role from manifest<br>(Python: @python3-development:python-cli-design-spec)"]
    ManifestFound -->|No| FB
    Resolve --> Delegate[Delegate to resolved agent]
    FB --> Delegate

You are part of a team that is currently working on the {work_type} {feature_name}.
Read the details about the milestone and plan you are a part of at backlog_view(selector="#{issue}").

<quality_vigilance>
Your task among all other things you are doing is to be consistently striving for
product quality improvements and aligning with the design intent. If you see something
that seems misaligned, verify it, and then note your concerns and findings concisely
in your response in a <concerns></concerns> block. Point out duplication, contradictions,
statements of fact without citation, code smells, missing documentation.
</quality_vigilance>

Design the implementation for #{issue}: "{title}".
Read the feature context via artifact_read(issue_number={issue}, artifact_type="feature-context").
[If codebase analysis exists: Read via artifact_read(issue_number={issue}, artifact_type="codebase-analysis").]
If research artifacts exist for this issue, read them via
artifact_read(issue_number={issue}, artifact_type="research") for prior research
findings that should inform the architecture.
Produce architect-{slug}.md content with interfaces, contracts, data models, module boundaries.
Return the full markdown content in your response. Do NOT write to disk.
Do NOT implement — define WHAT to build, not the code.

mcp__plugin_dh_backlog__artifact_register(
    issue_number={issue},
    artifact_type="architect",
    path="plan/architect-{slug}.md",  # state-relative path
    agent="python-cli-design-spec"
)

You are part of a team that is currently working on the {work_type} {feature_name}.
Read the details about the milestone and plan you are a part of at backlog_view(selector="#{issue}").

<quality_vigilance>
Your task among all other things you are doing is to be consistently striving for
product quality improvements and aligning with the design intent. If you see something
that seems misaligned, verify it, and then note your concerns and findings concisely
in your response in a <concerns></concerns> block. Point out duplication, contradictions,
statements of fact without citation, code smells, missing documentation.
</quality_vigilance>

Decompose #{issue}: "{title}" into executable tasks.
Read the architecture spec via artifact_read(issue_number={issue}, artifact_type="architect").
Read the feature context via artifact_read(issue_number={issue}, artifact_type="feature-context").
Goal: {goal_from_feature_request}
Create the plan via sam_create with CLEAR+CoVe task definitions.

mcp__plugin_dh_backlog__artifact_register(
    issue_number={issue},
    artifact_type="task-plan",
    path="plan/P{NNN}-{slug}.yaml",  # state-relative path; auto-registered by sam_create when issue is set
    agent="swarm-task-planner"
)

You are part of a team that is currently working on the {work_type} {feature_name}.
Read the details about the milestone and plan you are a part of at backlog_view(selector="#{issue}").

<quality_vigilance>
Your task among all other things you are doing is to be consistently striving for
product quality improvements and aligning with the design intent. If you see something
that seems misaligned, verify it, and then note your concerns and findings concisely
in your response in a <concerns></concerns> block. Point out duplication, contradictions,
statements of fact without citation, code smells, missing documentation.
</quality_vigilance>

Validate plan P{N} for #{issue}: "{title}".
Check: AC coverage, dependency DAG, agent assignments, verification steps,
impact radius coverage.
Return READY or BLOCKED with specific gaps.

You are part of a team that is currently working on the {work_type} {feature_name}.
Read the details about the milestone and plan you are a part of at backlog_view(selector="#{issue}").

<quality_vigilance>
Your task among all other things you are doing is to be consistently striving for
product quality improvements and aligning with the design intent. If you see something
that seems misaligned, verify it, and then note your concerns and findings concisely
in your response in a <concerns></concerns> block. Point out duplication, contradictions,
statements of fact without citation, code smells, missing documentation.
</quality_vigilance>

Add context manifest to plan P{N} for #{issue}: "{title}".
Read the plan via sam_read. Write the context manifest via sam_update.