What is thesis-resume?

A thesis-workflow recovery command that reads saved project files to find the current phase, completed steps, pending approvals, and next action.

It helps resume an active thesis project from its saved state and handle interrupted multi-step work.

It restores your place after a context reset, cleared session, or new session.

thesis-resume — Command for Claude Code by idoforgod

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/idoforgod/Dissertation-Simulator-AgenticWorkflow

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/idoforgod/dissertation-simulator-agenticworkflow/thesis-resume/github.svg)](https://agentmods.dev/commands/idoforgod/dissertation-simulator-agenticworkflow/thesis-resume)

Your own site

<a href="https://agentmods.dev/commands/idoforgod/dissertation-simulator-agenticworkflow/thesis-resume"><img src="https://agentmods.dev/badge/commands/idoforgod/dissertation-simulator-agenticworkflow/thesis-resume/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/idoforgod/dissertation-simulator-agenticworkflow/thesis-resume"><img src="https://agentmods.dev/badge/commands/idoforgod/dissertation-simulator-agenticworkflow/thesis-resume.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 555 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.

Model	Per session	Once invoked
Fable 5.1	$0.00022	$0.00555
Opus 5.5	$0.00009	$0.00222
Sonnet 5.5	$0.00004	$0.00111
Haiku 4.5	$0.00002	$0.00056

Measured 1mo ago against content hash 4b7fe1e96df9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

thesis-resume 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 1mo 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/commands/thesis-resume.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Thesis Resume

Recover thesis workflow state after context loss (compact/clear/new session).

Protocol

Step 1: Find Active Project

ls thesis-output/

If multiple projects exist, ask user which to resume.

Step 2: Read Recovery Files

Read these files in order (Context Reset Model from workflow.md):

thesis-output/{project}/session.json — Current SOT state
thesis-output/{project}/todo-checklist.md — Step completion status
thesis-output/{project}/research-synthesis.md — Accumulated insights

Step 3: Determine Resume Point

Based on SOT current_step, identify:

Which phase we're in
What was the last completed step
What is the next step to execute
Whether any gate is pending

Step 3.5: Check for Mid-Consolidation State

Use the P1 deterministic helper to compute the next execution step — handles consolidation restart logic automatically (no manual math required):

python3 "$CLAUDE_PROJECT_DIR"/.claude/hooks/scripts/query_step.py \
  --next-step --project-dir "$CLAUDE_PROJECT_DIR/thesis-output/{project}" --json

Output includes next_step, reason ("normal" or "restart_consolidated_group"), and consolidated_group (list of step numbers if applicable). If reason is "restart_consolidated_group", the entire group must be re-executed from next_step. This is also surfaced by restore_context.py in the IMMORTAL section.

Step 4: Restore Checkpoint (if available)

python3 "$CLAUDE_PROJECT_DIR"/.claude/hooks/scripts/checklist_manager.py \
  --status \
  --project-dir "$CLAUDE_PROJECT_DIR/thesis-output/{project}"

Step 5: Report Recovery (Korean)

Display:

Recovered project name and state
Current position in workflow
Last completed step
Execution mode (from SOT execution_mode field)
Next action
Any pending gates or HITL checkpoints

Step 6: Re-activate Execution Mode

Read execution_mode from SOT and re-activate the corresponding behavior per thesis-orchestrator's "Execution Mode Activation" table. This ensures Autopilot/ULW survive context resets.

Read the full file on GitHub · 75 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.

1mo ago First seen · 75 lines · 22 tokens per session scan A 4b7fe1e96df9

Subscribe to this mod's changes

thesis-resume is a command published in the GitHub repository idoforgod/Dissertation-Simulator-AgenticWorkflow (108 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 555 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.

Planning Productivity

thesis-resume