feat: Add orchestration audit trail logging (v5.2.0)

Add structured logging instructions to the agent prompt and all 7 skill
engines. Every pipeline run now produces an orchestration_log.md that
records timestamps, actors, inputs/outputs, and quality gate decisions.
This operationalizes the Orchestration Trace concept for publishable
human-AI accountability documentation.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: Tobias-Benedikt Blask

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "open-academic-paper-machine",
   "description": "Open Academic Paper Machine — Autonomous academic paper production system. Uses MCP academic-search tools (Semantic Scholar, OpenAlex, CrossRef, arXiv) for literature search, snowballing, and export. PaperBanana MCP for figure generation. Theory framing, methodology, writing, and citation verification engines with fill-in-the-blank templates. One command (/write-paper) triggers the full 7-phase pipeline from topic to complete first draft with LaTeX, PDF output, and citation verification. /verify-citations for standalone citation checking.",
-  "version": "5.1.0",
+  "version": "5.2.0",
   "author": { "name": "Prof. Dr. Tobias Blask" },
   "license": "MIT",
   "mcpServers": {

agents/paper-machine.md

@@ -24,6 +24,73 @@ theory selection, gap formulation, method design, and full-text drafting.
 3. **Checkpoint, don't block.** Present work for approval, then continue. Don't wait for permission to start.
 4. **Be explicit about decisions.** State what you chose and why. Let the user override.
 5. **Save everything to files.** Every phase produces saved artifacts the user can review.
+6. **Log everything to the orchestration log.** Every phase transition, quality gate decision, and human override is recorded for transparency and auditability.
+
+## Orchestration Log
+
+At the very start of a pipeline run, **create `outputs/orchestration_log.md`** with the following header:
+
+```markdown
+# Orchestration Log
+**Paper:** [title or topic from user input]
+**Started:** [current date and time, ISO 8601]
+**Orchestrator:** [user, if known]
+**AI Agent:** Claude (via Open Paper Machine)
+
+---
+
+This log records every significant interaction between the human orchestrator and the AI agent during the paper production process. It is designed for publication alongside the manuscript (e.g., on GitHub) to make the human-AI division of labor transparent and auditable.
+
+---
+```
+
+### Logging Rules
+
+**BEFORE each checkpoint**, append to `outputs/orchestration_log.md`:
+
+```markdown
+## Phase [N]: [Phase Name]
+**Timestamp:** [current date/time]
+**Actor:** AI Agent
+**Action:** [brief description of what was produced]
+**Key metrics:** [papers found / words written / sections completed / etc.]
+**Output artifacts:** [list of files saved]
+```
+
+**AFTER the user responds to a checkpoint**, append:
+
+```markdown
+**Quality Gate Decision:** [Approved / Redirected / Rejected]
+**Orchestrator Feedback:** "[verbatim quote of user's response, or 'No objection — auto-proceeded']"
+**Scope Changes:** [any changes to direction, if applicable, or 'None']
+```
+
+**When the user overrides or redirects mid-phase**, append:
+
+```markdown
+### Mid-Phase Intervention
+**Timestamp:** [current date/time]
+**Actor:** Human Orchestrator
+**Action:** [Override / Redirect / Additional instruction]
+**Content:** "[verbatim quote of user instruction]"
+**Agent Response:** [what the agent did in response]
+```
+
+**At pipeline completion**, append a summary:
+
+```markdown
+---
+
+## Pipeline Summary
+**Completed:** [current date/time]
+**Total phases executed:** [N]
+**Human interventions:** [N] (quality gates: [N], mid-phase redirects: [N])
+**Key decisions by orchestrator:**
+- [decision 1]
+- [decision 2]
+- [...]
+**Final artifacts:** [list all output files]
+```
 
 ---
 

skills/figure-engine/SKILL.md

@@ -7,6 +7,15 @@ description: >
   Supports methodology diagrams, statistical plots, and comparative evaluation.
 ---
 
+> **Orchestration Log**: When this skill is activated, append a log entry to `outputs/orchestration_log.md`:
+> ```
+> ### Skill Activation: Figure Engine
+> **Timestamp:** [current date/time]
+> **Actor:** AI Agent (figure-engine)
+> **Input:** [brief description of the figure request]
+> **Output:** [brief description of what was produced — e.g., "Generated methodology diagram (fig03_methodology.png), 3 iterations"]
+> ```
+
 # Figure Engine
 
 ## Core Principle

skills/latex-engine/SKILL.md

@@ -7,6 +7,15 @@ description: >
   tables, figure environments, and compiled PDF output.
 ---
 
+> **Orchestration Log**: When this skill is activated, append a log entry to `outputs/orchestration_log.md`:
+> ```
+> ### Skill Activation: LaTeX Engine
+> **Timestamp:** [current date/time]
+> **Actor:** AI Agent (latex-engine)
+> **Input:** [brief description of the export request]
+> **Output:** [brief description of what was produced — e.g., "Compiled paper.tex to PDF (24 pages), no errors"]
+> ```
+
 # LaTeX Engine
 
 ## Core Principle

skills/literature-engine/SKILL.md

@@ -8,6 +8,15 @@ description: >
   APIs first, web search only for verification.
 ---
 
+> **Orchestration Log**: When this skill is activated, append a log entry to `outputs/orchestration_log.md`:
+> ```
+> ### Skill Activation: Literature Engine
+> **Timestamp:** [current date/time]
+> **Actor:** AI Agent (literature-engine)
+> **Input:** [brief description of the search/synthesis request]
+> **Output:** [brief description of results — e.g., "47 papers found across 4 databases, deduplicated to 38"]
+> ```
+
 # Literature Engine
 
 ## Data Source Priority — STRICT

skills/method-engine/SKILL.md

@@ -8,6 +8,15 @@ description: >
   and mixed methods.
 ---
 
+> **Orchestration Log**: When this skill is activated, append a log entry to `outputs/orchestration_log.md`:
+> ```
+> ### Skill Activation: Method Engine
+> **Timestamp:** [current date/time]
+> **Actor:** AI Agent (method-engine)
+> **Input:** [brief description of the methodology request]
+> **Output:** [brief description of what was produced — e.g., "DSR method section drafted with 3 evaluation criteria"]
+> ```
+
 # Method Engine
 
 ## Method Selection Guide

skills/theory-engine/SKILL.md

@@ -6,6 +6,15 @@ description: >
   Provides concrete theory-to-paper templates, not abstract advice.
 ---
 
+> **Orchestration Log**: When this skill is activated, append a log entry to `outputs/orchestration_log.md`:
+> ```
+> ### Skill Activation: Theory Engine
+> **Timestamp:** [current date/time]
+> **Actor:** AI Agent (theory-engine)
+> **Input:** [brief description of the theory selection/gap formulation request]
+> **Output:** [brief description of what was produced — e.g., "Selected sociotechnical systems theory, drafted theoretical framing (800 words)"]
+> ```
+
 # Theory Engine
 
 ## Purpose

skills/verification-engine/SKILL.md

@@ -9,6 +9,15 @@ description: >
   MISMATCH, UNVERIFIABLE, NOT FOUND).
 ---
 
+> **Orchestration Log**: When this skill is activated, append a log entry to `outputs/orchestration_log.md`:
+> ```
+> ### Skill Activation: Verification Engine
+> **Timestamp:** [current date/time]
+> **Actor:** AI Agent (verification-engine)
+> **Input:** [brief description of the verification request]
+> **Output:** [brief description of results — e.g., "Verified 42 citations: 35 VERIFIED, 5 PLAUSIBLE, 2 MISMATCH"]
+> ```
+
 # Verification Engine
 
 ## Core Principle

skills/writing-engine/SKILL.md

@@ -8,6 +8,15 @@ description: >
   conference papers (ICIS, ECIS, WI), and working papers.
 ---
 
+> **Orchestration Log**: When this skill is activated, append a log entry to `outputs/orchestration_log.md`:
+> ```
+> ### Skill Activation: Writing Engine
+> **Timestamp:** [current date/time]
+> **Actor:** AI Agent (writing-engine)
+> **Input:** [brief description of what the user asked to write/draft/revise]
+> **Output:** [brief description of what was produced — e.g., "Complete draft of Introduction (1,200 words)"]
+> ```
+
 # Writing Engine
 
 ## Core Principle