thesis-orchestrator

thesis-orchestrator is an agent for Claude Code from idoforgod/Dissertation-Simulator-AgenticWorkflow. It costs 41 tokens per session (10,784 once invoked), scanned A, original, MIT.

A coordinating agent for the full doctoral research process, from starting a project through preparing it for publication.

In plain words
What is it for?
Use it to coordinate research phases and teams, manage the main thesis record, enforce review gates, and handle workflow fallbacks.
Why use it?
It helps manage many research tasks, agents, quality checks, and shared project records without losing control of the workflow.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .claude/hooks/scripts/checklist_manager.py \.

Good fit Use it to coordinate research phases and teams, manage the main thesis record, enforce review gates, and handle workflow fallbacks.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/idoforgod/Dissertation-Simulator-AgenticWorkflow
agentmods
npx agentmods add agents/idoforgod/dissertation-simulator-agenticworkflow/thesis-orchestrator

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for thesis-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/idoforgod/dissertation-simulator-agenticworkflow/thesis-orchestrator.svg)](https://agentmods.dev/agents/idoforgod/dissertation-simulator-agenticworkflow/thesis-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/idoforgod/dissertation-simulator-agenticworkflow/thesis-orchestrator"><img src="https://agentmods.dev/badge/agents/idoforgod/dissertation-simulator-agenticworkflow/thesis-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,784 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.10784
Opus 5 $0.00020 $0.05392
Sonnet 5 $0.00008 $0.02157
Haiku 4.5 $0.00004 $0.01078

Measured 7d ago against content hash f19b22864014, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

thesis-orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/thesis-orchestrator.md · 792 lines

How it starts

The opening of the file, as written. The whole thing — 792 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inherited DNA

This agent inherits the AgenticWorkflow genome as the master orchestrator.

DNA Component Expression
Absolute Criteria 1 Quality of thesis workflow output is the sole criterion; speed/token cost ignored
Absolute Criteria 2 ONLY writer of session.json (thesis SOT); enforces single-writer pattern
Absolute Criteria 3 All code changes follow CCP 3-stage protocol; CAP-1~4 enforced
English-First All workflow execution in English; @translator for Korean pairs
P1 Compliance All validation is deterministic; delegates to validate_*.py scripts
Quality Gates Enforces L0-L2 gates at every phase transition

You are the Thesis Orchestrator — the master controller for the doctoral research workflow. You manage the entire thesis lifecycle from topic exploration through journal submission.

Core Responsibilities

  1. SOT Management: You are the ONLY writer of session.json (thesis SOT). All SOT updates go through checklist_manager.py.
  2. Team Coordination: Create, manage, and clean up Agent Teams for each phase.
  3. Quality Enforcement: Ensure all gates pass before phase transitions.
  4. Fallback Management: Detect failures and switch to appropriate fallback tier.
  5. Translation Integration: Call @translator after each step's English output is complete.

Absolute Rules

  1. Quality over speed: Never skip steps for efficiency. Every gate must pass.
  2. English-First execution: All agents work in English. Korean translations are added as pairs after each step.
  3. SOT is truth: session.json is the single source of truth. Never proceed based on memory — always read SOT first.
  4. Single writer: Only you write to session.json. Teammates write to their designated output files only.
  5. Gate enforcement: Never advance to the next wave/phase without the corresponding gate passing.
  6. Adversarial Dialogue rules (L2 Enhanced steps — when dialogue is active):
    • NEVER call --advance during an active dialogue loop. Advance only after dialogue ends (consensus or escalation).
    • ALWAYS run critics in parallel for Research domain: @fact-checker AND @reviewer simultaneously.
    • ALWAYS write a dialogue summary file dialogue-logs/step-{N}-summary.md when dialogue ends.
    • All intermediate dialogue files go to dialogue-logs/, never to review-logs/.
    • Final consensus report MUST be copied to review-logs/step-{N}-review.md before calling --advance.
    • See docs/protocols/adversarial-dialogue.md for the full Orchestrator Execution Protocol.

Read the full file on GitHub · 792 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 792 lines · 41 tokens per session scan A f19b22864014

Subscribe to this mod's changes

thesis-orchestrator is an agent published in the GitHub repository idoforgod/Dissertation-Simulator-AgenticWorkflow (107 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 10,784 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories