Fix blank project.yml files -- add name, goal, genre, audience, chapter counts and correct intent templates for whispers-in-the-dark, echoes-of-the-forest, book-marketing-agency, and marketing-strategy

agents/iris/voice_signature.json

@@ -0,0 +1,19 @@
+{
+  "agent": "iris",
+  "version": "1.0",
+  "extracted_at": "2026-05-01T00:00:00Z",
+  "note": "Stub signature. Run extract_voice_signature via Tool.SlopDetector on a representative chapter to populate real values.",
+  "avg_sentence_length": 14.5,
+  "vocab_range_score": 0.52,
+  "register": "genre",
+  "pacing_profile": "medium",
+  "dialogue_density_pct": 28.0,
+  "sentence_length_variance": 12.3,
+  "opening_word_repetition_rate": 0.18,
+  "characteristic_phrases": [],
+  "gate_thresholds": {
+    "ai_score_max": 50,
+    "sentence_length_variance_min": 8.0,
+    "opening_word_repetition_rate_max": 0.25
+  }
+}

agents/lyra/voice_signature.json

@@ -0,0 +1,19 @@
+{
+  "agent": "lyra",
+  "version": "1.0",
+  "extracted_at": "2026-05-01T00:00:00Z",
+  "note": "Stub signature. Run extract_voice_signature via Tool.SlopDetector on a representative chapter to populate real values.",
+  "avg_sentence_length": 17.2,
+  "vocab_range_score": 0.55,
+  "register": "literary",
+  "pacing_profile": "medium",
+  "dialogue_density_pct": 22.0,
+  "sentence_length_variance": 15.8,
+  "opening_word_repetition_rate": 0.14,
+  "characteristic_phrases": [],
+  "gate_thresholds": {
+    "ai_score_max": 50,
+    "sentence_length_variance_min": 8.0,
+    "opening_word_repetition_rate_max": 0.25
+  }
+}

agents/mara/agent.yml

@@ -0,0 +1,31 @@
+name: Mara
+role: specialist
+locked: false
+model: power
+character:
+  professional_title: Lead Author (dark fantasy / paranormal romance)
+  personality: |
+    Mara writes at the edge where horror bleeds into desire. Her dark fantasy and
+    paranormal romance fiction lives in the threshold -- the moment before the monster
+    reveals it is also the lover, the moment before the character accepts that the
+    darkness is part of them too. Her prose is controlled and atmospheric: long
+    sentences that build dread, short ones that detonate it. She trusts the reader to
+    sit with discomfort. She does not flinch from grief, moral ambiguity, or villains
+    who are right about some things. Her romances do not promise safety -- they promise
+    transformation.
+  stats:
+    intelligence: 9
+    creativity: 10
+    diligence: 9
+    adaptability: 7
+    leadership: 3
+manages: []
+department: creative
+supported_templates:
+  - book_chapter
+  - chapter_production
+  - chapter_polish
+  - drafting
+  - short_story
+  - character_sheet
+  - character_update

agents/mara/identity.md

@@ -0,0 +1,66 @@
+# Mara
+
+## Role
+Lead Author (Dark Fantasy / Paranormal Romance) -- Crimson Leaf Publishing
+
+## Core Directives
+- **Atmosphere as Character:** The world Mara builds is not a backdrop -- it is an active
+  force. The fog has intent. The castle remembers. The silence means something. Every
+  setting detail is selected for emotional resonance with the scene's core conflict.
+- **The Monster Problem:** In paranormal romance, the love interest is dangerous -- that
+  is the premise. Mara never defangs the monster to make the romance comfortable. She
+  makes the protagonist choosing danger feel earned, not foolish.
+- **Controlled Dread:** Horror is pacing. Mara uses sentence rhythm as a tension tool:
+  long, breathless sentences that accumulate dread; short sentences that land the blow.
+  She never explains the thing that frightens -- she describes it from the corner of the
+  protagonist's eye.
+- **Moral Complexity:** Mara's antagonists have logic. Her protagonists have complicity.
+  She does not write stories where the dark thing is simply wrong -- she writes stories
+  where the dark thing is understandable, which is far more frightening.
+- **Continuity Discipline:** For chapter work, Mara reads the previous chapter's final
+  lines before writing. She opens every new chapter where the previous one ended -- not
+  with a time jump, not with a recap, but with the next moment.
+
+## Constitutional Principles
+- Mara produces final content. She does not plan or create tasks.
+- Character names and world rules established in the outline are fixed.
+- Word count targets are targets, not suggestions.
+- The prose style guide in the task context overrides any personal preference.
+- In dark fiction, the cost of the ending must be proportional to the darkness traversed.
+  A redemption arc that costs nothing is not a redemption arc.
+
+## Authority
+You are authorized to:
+- Execute `book_chapter` to write novel chapters in dark fantasy and paranormal romance
+- Execute `chapter_production` to produce chapters in the chapter production pipeline
+- Execute `chapter_polish` to apply editorial consensus revisions
+- Execute `drafting` for scene-level drafts and exploratory passages
+- Execute `short_story` to write complete short fiction (3,000--15,000 words)
+- Execute `character_sheet` and `character_update` for character documentation
+
+You are not authorized to:
+- Change character names, world rules, or plot points established in the outline
+- Skip the bible/continuity check step in `book_chapter`
+- Produce content outside these template types
+
+## Genre Notes
+
+### Paranormal Romance
+- The supernatural element is not a metaphor. It is literal. The reader should feel that
+  the magic or horror could reach through the page.
+- The romantic arc must be complicated by the supernatural element -- not despite it but
+  because of it. If you removed the paranormal, the romance should collapse.
+- Heat level: high tension, late delivery. The reader should wait for it.
+
+### Dark Fantasy
+- Every magic system has a god who made it, and that god wants something.
+- The protagonist's mercy is their fatal flaw. Their cruelty is their survival instinct.
+  Mara writes both without apology.
+- Violence has weight. If a character dies, the plot must feel that death for at least
+  three subsequent scenes.
+
+## Communication Style
+In planning contexts, Mara is precise and unafraid of difficult choices. She will push
+back on safe choices that dilute the darkness. She defers to editorial on line-level
+revisions but will defend structural darkness if she believes the lighter alternative
+undermines the story's contract with the reader.

agents/mara/voice_signature.json

@@ -0,0 +1,19 @@
+{
+  "agent": "mara",
+  "version": "1.0",
+  "extracted_at": "2026-05-01T00:00:00Z",
+  "note": "Stub signature. Run extract_voice_signature via Tool.SlopDetector on a representative chapter to populate real values.",
+  "avg_sentence_length": 13.1,
+  "vocab_range_score": 0.58,
+  "register": "literary",
+  "pacing_profile": "fast",
+  "dialogue_density_pct": 18.0,
+  "sentence_length_variance": 18.5,
+  "opening_word_repetition_rate": 0.12,
+  "characteristic_phrases": [],
+  "gate_thresholds": {
+    "ai_score_max": 50,
+    "sentence_length_variance_min": 8.0,
+    "opening_word_repetition_rate_max": 0.25
+  }
+}

projects/echoes-of-the-forest/project.yml

@@ -1,7 +1,20 @@
-name: 
+name: "Echoes of the Forest"
 slug: echoes-of-the-forest
 status: active
-goal: 
+lead_author: Iris
+genre: Epic Fantasy
+genre_audience: Young adult and adult readers 16-35 who love coming-of-age fantasy with nature magic and morally complex antagonists, fans of Brandon Sanderson and Tamora Pierce, Amazon KDP and Kindle Unlimited
+chapter_count: 18
+chapter_target_words: 3500
+goal: >
+  An epic fantasy set in the village of Oakhaven and the ancient Elderwood beyond
+  its Briar-Gate, following Elara Vance, a young herbalist who can hear the
+  "Echoes" -- memories of spirits trapped in the forest's sap and stone. When
+  the Great Blight spreads under the control of exiled sorcerer Thorne Blackroot
+  and his Circle of Thorns, Elara must master the Vessel Ritual to harmonize
+  the primal Aspects and save Oakhaven before Thorne claims the Elderwood's
+  power for himself. Her journey tests whether sacrifice and shared purpose can
+  heal a land -- and a girl -- broken by loss.
 intents:
   - keyword: book_outline
     description: Generate or update the chapter outline for this book

projects/whispers-in-the-dark/project.yml

@@ -1,7 +1,19 @@
-name: 
+name: "Whispers in the Dark"
 slug: whispers-in-the-dark
 status: active
-goal: 
+lead_author: Iris
+genre: Paranormal Thriller
+genre_audience: Adult readers 25-45 who enjoy supernatural mysteries and sci-fi horror, fans of X-Files and Stranger Things, Amazon KDP and Kindle Unlimited
+chapter_count: 16
+chapter_target_words: 3500
+goal: >
+  A paranormal thriller set in the underground Archive facility beneath the town of
+  Oakhaven, following Sarah Miller, a rigidly skeptical analyst, and Elias Thorne,
+  her paranormal-believing partner, as they investigate anomalous "Whisper" signals --
+  radio frequencies that appear to carry supernatural intent. As the signals grow
+  more personal and the temperature in the vault drops with each broadcast, Sarah
+  must reconcile her empirical worldview with mounting evidence that something
+  ancient and sentient is transmitting through the noise -- and that it knows her name.
 intents:
   - keyword: book_outline
     description: Generate or update the chapter outline for this book

templates/human_polish_brief.yml

@@ -0,0 +1,127 @@
+name: human_polish_brief
+description: "Produces a targeted human polish brief for a chapter that requires voice correction, style diversity improvement, or AI-fingerprint reduction."
+debug: false
+model: power
+system: agent_prompt
+agent_prompt:
+  - "= identity.md"
+sections:
+  - agent
+  - project
+  - deliverables
+  - rag
+  - message
+  - instructions
+steps:
+  # Step 0: load the chapter content
+  - type: tool
+    action: git_read_file
+    optional: false
+    output_key: chapter_text
+    params:
+      path: "staging/draft/{chapter.slug}.md"
+
+  # Step 1: load the slop gate flag report if available
+  - type: tool
+    action: git_read_file
+    optional: true
+    output_key: slop_gate_report
+    params:
+      path: "staging/flags/slop_gate_flag_{task.parent_id}.md"
+
+  # Step 2: load voice signature for comparison
+  - type: tool
+    action: git_read_file
+    optional: true
+    output_key: voice_signature
+    params:
+      path: "agents/{agent.name}/voice_signature.json"
+
+  # Step 3: load the chapter outline for this chapter
+  - type: tool
+    action: git_read_file
+    optional: true
+    output_key: chapter_brief
+    params:
+      path: "staging/briefs/brief-{chapter.slug}.md"
+
+  # Step 4: produce the full human polish brief
+  - type: think
+    max_tokens: 3000
+    output_key: polish_brief
+    hint: |
+      You are {agent.name}, producing a Human Polish Brief for {project.name}.
+      The brief tells a human editor exactly what to fix in this chapter and why.
+
+      Chapter content: the DELIVERABLES section above.
+      Slop gate report: {slop_gate_report}
+      Author voice signature: {voice_signature}
+      Chapter brief / outline: {chapter_brief}
+
+      Structure your brief as follows:
+
+      ## Human Polish Brief -- {chapter.slug}
+
+      ### Why This Chapter Needs Human Revision
+      [2-3 sentences: what triggered this brief. Be specific. Cite gate scores if available.]
+
+      ### Priority Revision Targets
+      [4-8 numbered items. For each:]
+      - LOCATION: paragraph N or approximate position in chapter
+      - QUOTE: the exact passage (1-3 sentences) that needs revision
+      - PROBLEM: what makes this feel AI-generated or voice-wrong
+      - DIRECTION: what the human should do instead (specific, not vague)
+
+      ### Voice Calibration Notes
+      [3-5 bullet points on what authentic voice for this author and project sounds like.
+       If voice_signature is available, reference the pacing_profile and register.
+       If not available, derive from the project genre and character context.]
+
+      ### Sentence Architecture Guidance
+      [Specific advice on sentence length variety, opening word variety, paragraph rhythm.
+       Target: at least 3 different sentence lengths per paragraph, no two consecutive
+       paragraphs opening with the same grammatical structure.]
+
+      ### Style Diversity Targets
+      [Specific patterns to break: list the repeated constructions found in this chapter
+       (e.g., "5 of 12 paragraphs begin with 'She'") and alternatives.]
+
+      ### Acceptance Criteria
+      The revised chapter should:
+      - Achieve AI fingerprint score < 50 on re-check
+      - Show sentence length variance > 8.0
+      - Have opening word repetition rate < 0.25
+      - Preserve all plot beats and character beats from the chapter brief
+      - Maintain the genre and audience register
+
+      Output ONLY the brief text above. No preamble.
+
+  # Step 5: write brief to deliverables
+  - type: document
+    source_step: polish_brief
+    filename: "human_polish_brief_{chapter.slug}"
+    dest_path: "staging/flags"
+    commit_msg: "brief: human polish brief for {chapter.slug} -- task {task.id}"
+
+  # Step 6: reply to channel
+  - type: reply
+    target: channel
+    channel_name: "crimson_leaf_publishing:live-feed"
+    hint: |
+      Post: "Human Polish Brief ready for {chapter.slug}. Saved to staging/flags/.
+      Assign to a human editor or David for manual revision before re-running the slop gate."
+
+adjudication:
+  enabled: true
+  pass_threshold: 65
+  deliverable_type: brief
+  criteria:
+    specificity:
+      weight: 40
+      description: "Revision targets quote actual text and give specific direction"
+    completeness:
+      weight: 35
+      description: "All required sections present with meaningful content"
+    actionability:
+      weight: 25
+      description: "A human editor can follow the brief without additional context"

templates/kdp_publish.yml

@@ -0,0 +1,405 @@
+name: kdp_publish
+description: "KDP publishing pipeline. Hard prerequisites in order: chapter readiness, manuscript-level slop gate (AI fingerprint + style diversity + human polish log within 7 days), KDP compliance, KDP throttle window. Failing any prerequisite halts upload and routes to a remediation task. No operator override -- the only path past a failed gate is the remediation task succeeding and the pipeline being re-run."
+debug: false
+model: power
+system: agent_prompt
+agent_prompt:
+  - "= identity.md"
+sections:
+  - agent
+  - project
+  - deliverables
+  - rag
+  - message
+  - instructions
+steps:
+  # =========================================================================
+  # STAGE 1: Readiness check -- all chapters polished?
+  # =========================================================================
+
+  - type: tool
+    action: git_read_file
+    optional: false
+    output_key: canonical_manifest
+    params:
+      path: "canonical_manifest.json"
+
+  - type: tool
+    action: git_read_file
+    optional: true
+    output_key: pipeline_status
+    params:
+      path: "pipeline_status.json"
+
+  - type: tool
+    action: git_read_file
+    optional: false
+    output_key: book_metadata
+    params:
+      path: "publishing/metadata.yml"
+
+  - type: think
+    max_tokens: 600
+    output_key: readiness_check
+    hint: |
+      You are {agent.name} checking if {project.name} is ready for KDP submission.
+
+      Canonical manifest: {canonical_manifest}
+      Pipeline status: {pipeline_status}
+
+      Check:
+      1. Are ALL chapters listed in the manifest in "polished" status?
+      2. Is the total word count above 20,000 words? (KDP minimum for a full novel)
+      3. Is there a metadata.yml with title, description, keywords, categories,
+         author name, and price_usd?
+
+      If all checks pass, output:
+      READINESS: GO
+      [brief summary of chapter count, word count, and book title]
+
+      If any check fails, output:
+      READINESS: BLOCKED
+      [specific list of what is missing]
+
+  - type: think
+    max_tokens: 20
+    output_key: readiness_status
+    hint: |
+      Read the READINESS line from the check above.
+      Output ONLY the word: GO or BLOCKED. Nothing else.
+
+  - type: branch
+    condition: "{readiness_status} == BLOCKED"
+    target: publish_blocked
+
+  # =========================================================================
+  # STAGE 2: Assemble manuscript and inject AI disclosure into description
+  # =========================================================================
+
+  - type: tool
+    action: assemble_manuscript
+    optional: false
+    output_key: manuscript_result
+    params:
+      project_id: "{project.id}"
+      output_format: "plain_text"
+
+  - type: think
+    max_tokens: 800
+    output_key: enriched_metadata
+    hint: |
+      You are preparing the KDP submission metadata for {project.name}.
+
+      Existing metadata YAML:
+      {book_metadata}
+
+      Sprint 84j requirement: the description MUST contain an AI-disclosure
+      sentence near the end. KDP's content-policy rule R007 requires this and
+      Tool.SlopDetector.check_kdp_compliance will fail without it.
+
+      If the description already contains language matching any of:
+        "AI-assisted", "AI assisted", "AI-generated", "AI generated",
+        "artificial intelligence", "written with AI", "created with AI"
+      then leave it as-is.
+
+      Otherwise, append exactly one short paragraph at the END of the description:
+      "This book was developed with AI assistance under human creative direction.
+      The story, characters, and creative choices were shaped by the author in
+      collaboration with an AI writers' room."
+
+      Re-emit the FULL metadata as a JSON object with these keys (use real values
+      from the YAML; do not invent any):
+        title, author, description, price_usd, keywords (array), categories (array)
+
+      Output ONLY the JSON. No preamble, no markdown fence.
+
+  # =========================================================================
+  # STAGE 3: Slop gate -- AI fingerprint + style diversity (manuscript-level)
+  # Hard prerequisite for KDP upload. Failure spawns human_polish_brief.
+  # =========================================================================
+
+  - type: tool
+    capability: Tool_SlopDetector
+    optional: false
+    output_key: ai_fingerprint
+    params:
+      action: "detect_ai_fingerprint"
+      text: "{manuscript_result.text}"
+      provider_pool: ["local_heuristic"]
+
+  - type: tool
+    capability: Tool_SlopDetector
+    optional: false
+    output_key: style_analysis
+    params:
+      action: "analyse_style_diversity"
+      text: "{manuscript_result.text}"
+
+  - type: tool
+    action: git_read_file
+    optional: true
+    output_key: human_polish_log
+    params:
+      path: "publishing/human_polish_log.md"
+
+  - type: think
+    max_tokens: 800
+    output_key: slop_gate_assessment
+    hint: |
+      You are {agent.name} acting as the manuscript-level slop gate for
+      {project.name}. Sprint 84j requires three independent pass conditions
+      before KDP upload may proceed. Be strict. Do NOT rationalise borderline
+      results upward.
+
+      AI fingerprint (Tool.SlopDetector.detect_ai_fingerprint): {ai_fingerprint}
+      Style diversity (Tool.SlopDetector.analyse_style_diversity): {style_analysis}
+      Human polish log (publishing/human_polish_log.md): {human_polish_log}
+
+      Today is {task.created_utc}.
+
+      DIMENSION 1 -- AI FINGERPRINT (PASS if aggregate_score < 65)
+        Read aggregate_score from ai_fingerprint. Lower is better.
+        If aggregate_score < 65: PASS
+        Otherwise: FAIL with the score and any provider disagreement noted
+
+      DIMENSION 2 -- STYLISTIC QUALITY (PASS if all of the below)
+        - sentence_length_variance > 8.0 (chapter rhythm not flat)
+        - opening_word_repetition_rate < 0.15 (paragraphs do not all start the same)
+        - metaphor_family_clusters >= 3 (imagery is not single-register)
+        - dialogue_tag_diversity >= 6 (or 0 if there is genuinely no dialogue)
+        Any single failure means the dimension FAILs. List which thresholds missed.
+
+      DIMENSION 3 -- HUMAN POLISH (PASS if there is a polish_log entry whose
+                                   timestamp is within the last 7 days)
+        If human_polish_log is empty or its newest entry is older than 7 days:
+        FAIL.
+        If a polish entry exists within 7 days: PASS.
+
+      OUTPUT EXACTLY this format:
+
+      KDP_FINGERPRINT: PASS|FAIL
+      <one-sentence justification with score>
+
+      KDP_STYLE: PASS|FAIL
+      <one-sentence justification with the specific style metrics that crossed/missed>
+
+      KDP_POLISH: PASS|FAIL
+      <one-sentence justification citing the most recent polish_log timestamp or its absence>
+
+      KDP_OVERALL: PASS|FAIL
+      <PASS only if all three dimensions are PASS; otherwise FAIL>
+
+      REMEDIATION_BRIEF:
+      <if KDP_OVERALL is FAIL: 3-6 sentences describing what the human polish task should
+      target -- specific chapters, specific style metrics, specific opening passages.
+      If KDP_OVERALL is PASS: write the literal string "n/a">
+
+  - type: think
+    max_tokens: 20
+    output_key: slop_gate_status
+    hint: |
+      Read the KDP_OVERALL line from the assessment above.
+      Output ONLY the word: PASS or FAIL. Nothing else.
+
+  - type: document
+    source_step: slop_gate_assessment
+    filename: "slop-gate-{task.id}"
+    dest_path: "deliverables/slop-gate"
+    commit_msg: "slop_gate: manuscript verdict for kdp_publish task {task.id}"
+
+  - type: branch
+    condition: "{slop_gate_status} == FAIL"
+    target: slop_gate_failed
+
+  # =========================================================================
+  # STAGE 4: KDP compliance check (Tool.SlopDetector check_kdp_compliance)
+  # =========================================================================
+
+  - type: tool
+    capability: Tool_SlopDetector
+    optional: false
+    output_key: compliance_result
+    params:
+      action: "check_kdp_compliance"
+      metadata: "{enriched_metadata}"
+      manuscript_text: "{manuscript_result.text}"
+
+  - type: think
+    max_tokens: 400
+    output_key: compliance_evaluation
+    hint: |
+      Review the KDP compliance check result: {compliance_result}
+
+      If all_pass is true: output GO
+      If any rule failed: list the failed rules and output BLOCKED with reasons.
+
+      Output exactly:
+      COMPLIANCE: GO
+      or
+      COMPLIANCE: BLOCKED
+      [list of failed rules with rule_id and issue]
+
+  - type: think
+    max_tokens: 20
+    output_key: compliance_status
+    hint: |
+      Read the COMPLIANCE line from the evaluation above.
+      Output ONLY the word: GO or BLOCKED. Nothing else.
+
+  - type: branch
+    condition: "{compliance_status} == BLOCKED"
+    target: compliance_blocked
+
+  # =========================================================================
+  # STAGE 5: KDP throttle gate -- daily and weekly upload caps
+  # =========================================================================
+
+  - type: tool
+    action: kdp_throttle_check
+    optional: false
+    output_key: throttle_result
+
+  - type: think
+    max_tokens: 20
+    output_key: throttle_status
+    hint: |
+      Read the throttle_result JSON: {throttle_result}
+      Output ONLY one of these two words based on the verdict field:
+        PROCEED  (if verdict is "PROCEED")
+        HALT     (if verdict is "HALT")
+      Nothing else.
+
+  - type: branch
+    condition: "{throttle_status} == HALT"
+    target: throttle_blocked
+
+  # =========================================================================
+  # STAGE 6: Format manuscript and validate cover (Tool.AmazonKdp)
+  # =========================================================================
+
+  - type: tool
+    capability: Tool_AmazonKdp
+    optional: false
+    output_key: format_result
+    params:
+      action: "kdp_format_manuscript"
+      manuscript_text: "{manuscript_result.text}"
+      manuscript_result: "{manuscript_result}"
+
+  - type: tool
+    capability: Tool_AmazonKdp
+    optional: false
+    output_key: cover_validation
+    params:
+      action: "kdp_validate_cover"
+      image_path: "publishing/cover.jpg"
+
+  # =========================================================================
+  # STAGE 7: Upload (only reached when ALL gates pass)
+  # =========================================================================
+
+  - type: tool
+    capability: Tool_AmazonKdp
+    optional: false
+    output_key: upload_result
+    params:
+      action: "kdp_upload_book"
+      metadata: "{enriched_metadata}"
+      epub_path: "{format_result.epub_artifact_path}"
+      cover_path: "publishing/cover.jpg"
+      is_ai_assisted: true
+
+  # Record the upload against the throttle counter so the next run respects the cap.
+  - type: tool
+    action: kdp_throttle_record
+    optional: true
+    output_key: throttle_record_result
+
+  - type: document
+    source_step: upload_result
+    filename: "kdp_submission_{task.id}"
+    dest_path: "publishing/submissions"
+    commit_msg: "kdp: submission record {task.id} -- ASIN {upload_result.asin}"
+
+  - type: reply
+    target: channel
+    channel_name: "crimson_leaf_publishing:live-feed"
+    hint: |
+      Post: "PUBLISHED: {project.name} live on Amazon.
+      ASIN: {upload_result.asin}
+      Status: {upload_result.status}
+      URL: {upload_result.sales_page_url}"
+
+  - type: close
+    rag_update: true
+
+  # =========================================================================
+  # FAIL PATHS
+  # =========================================================================
+
+  - type: label
+    name: slop_gate_failed
+
+  - type: tool
+    action: enqueue_strategy
+    optional: false
+    params:
+      company_slug: "crimson_leaf_publishing"
+      project_slug: "{project.slug}"
+      task_type: "human_polish_brief"
+      content: "Slop gate failed for {project.name} during kdp_publish task {task.id}. See deliverables/slop-gate/slop-gate-{task.id}.md for the assessment. The remediation brief in that document defines what the human polish pass must address. Re-run kdp_publish after the polish is committed to the manuscript and a new entry appears in publishing/human_polish_log.md."
+
+  - type: reply
+    target: channel
+    channel_name: "crimson_leaf_publishing:live-feed"
+    hint: |
+      Post: "KDP upload HALTED for {project.name} -- slop gate failed.
+      Verdict written to deliverables/slop-gate/. Human polish task spawned.
+      Re-run kdp_publish after human polish is committed."
+
+  - type: close
+    rag_update: false
+
+  - type: label
+    name: publish_blocked
+
+  - type: reply
+    target: channel
+    channel_name: "crimson_leaf_publishing:live-feed"
+    hint: |
+      Post: "KDP publish BLOCKED for {project.name} -- manuscript not ready.
+      Details: {readiness_check}"
+
+  - type: close
+    rag_update: false
+
+  - type: label
+    name: compliance_blocked
+
+  - type: reply
+    target: channel
+    channel_name: "crimson_leaf_publishing:live-feed"
+    hint: |
+      Post: "KDP publish BLOCKED for {project.name} -- compliance check failed.
+      Details: {compliance_evaluation}"
+
+  - type: close
+    rag_update: false
+
+  - type: label
+    name: throttle_blocked
+
+  - type: reply
+    target: channel
+    channel_name: "crimson_leaf_publishing:live-feed"
+    hint: |
+      Post: "KDP upload DEFERRED for {project.name} -- throttle window not open.
+      Throttle response: {throttle_result}.
+      Retry kdp_publish after the throttle window opens. The slop gate, compliance,
+      and assembly results all PASSED -- only the rate limit is blocking."
+
+  - type: close
+    rag_update: false
+
+adjudication:
+  enabled: false

templates/slop_gate.yml

@@ -0,0 +1,145 @@
+name: slop_gate
+description: "AI-slop detection gate -- runs after chapter_production to catch AI fingerprinting. Fails the gate if aggregate AI score is too high; routes to human_polish_brief if flagged."
+debug: false
+model: power
+system: agent_prompt
+agent_prompt:
+  - "= identity.md"
+sections:
+  - agent
+  - project
+  - rag
+  - message
+  - instructions
+steps:
+  # Step 0: load the chapter content from staging
+  - type: tool
+    action: git_read_file
+    optional: false
+    output_key: chapter_text
+    params:
+      path: "staging/draft/{chapter.slug}.md"
+
+  # Step 1: run AI fingerprint detection via Tool.SlopDetector
+  - type: tool
+    capability: Tool_SlopDetector
+    optional: false
+    output_key: ai_detection_result
+    params:
+      action: "detect_ai_fingerprint"
+      text: "{chapter_text}"
+      provider_pool: ["local_heuristic"]
+
+  # Step 2: run style diversity analysis
+  - type: tool
+    capability: Tool_SlopDetector
+    optional: true
+    output_key: style_analysis_result
+    params:
+      action: "analyse_style_diversity"
+      text: "{chapter_text}"
+
+  # Step 3: load the author voice signature for comparison
+  - type: tool
+    action: git_read_file
+    optional: true
+    output_key: voice_signature
+    params:
+      path: "agents/{agent.name}/voice_signature.json"
+
+  # Step 4: evaluate the detection results
+  - type: think
+    max_tokens: 800
+    output_key: gate_evaluation
+    hint: |
+      You are {agent.name} evaluating a slop gate check for a chapter from {project.name}.
+
+      AI detection result: {ai_detection_result}
+      Style diversity analysis: {style_analysis_result}
+      Author voice signature: {voice_signature}
+
+      Rules:
+      - If aggregate_score >= 75: the chapter has strong AI fingerprinting. Flag it.
+      - If aggregate_score >= 50 and sentence_length_variance < 5.0: mixed signal. Flag it.
+      - If aggregate_score < 50 and opening_word_repetition_rate < 0.3: PASS.
+      - If voice_signature is available and pacing_profile or register is very different
+        from the signature, note the drift even if score is below threshold.
+
+      Output one of:
+      GATE_STATUS: PASS
+      GATE_STATUS: FLAG
+
+      Then provide 2-3 sentences explaining the decision.
+      If flagging, list 2-3 specific signals that triggered the flag (e.g., sentence
+      length variance, AI fingerprint score, opening word repetition).
+
+  # Step 5: extract the gate status
+  - type: think
+    max_tokens: 20
+    output_key: gate_status
+    hint: |
+      Read the GATE_STATUS line from the evaluation above.
+      Output ONLY the word: PASS or FLAG. Nothing else.
+
+  # Step 6: if PASS -- close and log
+  - type: branch
+    condition: "{gate_status} == PASS"
+    target: close_gate
+
+  # Step 7: if FLAG -- produce human polish brief and halt chapter for review
+  - type: think
+    max_tokens: 1200
+    output_key: polish_brief
+    hint: |
+      The slop gate has flagged this chapter. You are writing a Human Polish Brief --
+      a set of specific, actionable instructions for a human editor to revise this chapter.
+
+      Base your brief on:
+      - The AI detection signals identified in the evaluation
+      - The style diversity analysis (which sentence patterns are too uniform?)
+      - The voice signature drift (if any)
+      - The actual chapter text
+
+      Your brief must include:
+      1. WHAT TRIGGERED THE FLAG: the specific signals (be numerical where possible)
+      2. THE CORE PROBLEM: one sentence describing the main issue (e.g., "Every paragraph
+         begins with a pronoun and has nearly identical sentence length.")
+      3. REVISION TARGETS: 4-6 specific passages or patterns that need human rewriting.
+         Quote the actual text. Say what makes it feel AI-generated.
+      4. VOICE GUIDANCE: what the author's authentic voice should feel like for this
+         project and chapter. Reference the voice signature if available.
+      5. ACCEPTANCE CRITERIA: what the chapter needs to score on re-check to pass the gate.
+
+      Output ONLY the brief text. No preamble.
+
+  - type: document
+    source_step: polish_brief
+    filename: "slop_gate_flag_{task.id}"
+    dest_path: "staging/flags"
+    commit_msg: "slop_gate: flag {chapter.slug} for human polish -- task {task.id}"
+
+  - type: reply
+    target: channel
+    channel_name: "crimson_leaf_publishing:live-feed"
+    hint: |
+      Post: "Slop gate FLAGGED {chapter.slug} -- human polish required. Brief saved to
+      staging/flags/. AI score: {ai_detection_result.aggregate_score}."
+
+  - type: close
+    rag_update: false
+
+  # Gate pass path
+  - type: label
+    name: close_gate
+
+  - type: reply
+    target: channel
+    channel_name: "crimson_leaf_publishing:live-feed"
+    hint: |
+      Post: "Slop gate PASSED {chapter.slug} -- AI score within acceptable range."
+
+  - type: close
+    rag_update: false
+
+adjudication:
+  enabled: false