claude-sisyphus-grad: Command for Claude Code

.claude/commands/research-state.md

research-state is a command for Claude Code from Hwiyeon/claude-sisyphus-grad. It costs 0 tokens per session (1,557 once invoked), scanned A, original, MIT.

A command that refreshes a compact document showing the current state of a research project. It can also create a standalone copy by inserting the contents of referenced files.

In plain words
What is it for?
Use it to update research/state.md, optionally synchronize selected README sections, or export a self-contained state document for external AI tools.
Why use it?
It helps someone quickly resume research or share the active thread and decisions with another AI without reading the entire research history.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is Hwiyeon/claude-sisyphus-grad's own configuration. It tells Claude Code how to work on claude-sisyphus-grad itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-sisyphus-grad configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Hwiyeon/claude-sisyphus-grad. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Hwiyeon/claude-sisyphus-grad/main/.claude/commands/research-state.md
Clone the repo
git clone --depth 1 https://github.com/Hwiyeon/claude-sisyphus-grad

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 research-state

README.md
[![agentmods](https://agentmods.dev/badge/commands/hwiyeon/claude-sisyphus-grad/research-state/github.svg)](https://agentmods.dev/commands/hwiyeon/claude-sisyphus-grad/research-state)
Your own site
<a href="https://agentmods.dev/commands/hwiyeon/claude-sisyphus-grad/research-state"><img src="https://agentmods.dev/badge/commands/hwiyeon/claude-sisyphus-grad/research-state/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.

agentmods 80×15 button for research-state

Your own site · 80×15
<a href="https://agentmods.dev/commands/hwiyeon/claude-sisyphus-grad/research-state"><img src="https://agentmods.dev/badge/commands/hwiyeon/claude-sisyphus-grad/research-state.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,557 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 $0.00000 $0.01557
Opus 5 $0.00000 $0.00779
Sonnet 5 $0.00000 $0.00311
Haiku 4.5 $0.00000 $0.00156

Measured 11d ago against content hash b7f47c12e41d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

research-state 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 11d 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/research-state.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/research-state — Update research/state.md (with optional README sync & standalone export)

Updates the project's research state snapshot — a single-file "where we are right now" document designed for fast re-entry and external LLM sharing.

state.md sits between two other views:

  • /discuss cache (~full index, 100K+ tokens, internal use)
  • README.md (human-readable summary, history-oriented)

state.md is optimized for a different use case: a compact (~3–5K tokens) always-current "single active thread + decision tree" snapshot you can paste into ChatGPT/Gemini or skim after a break.

Two modes:

  • default — refresh research/state.md (AUTO sections auto, MANUAL sections via Claude proposal + user approval). Optionally sync stale README sections.
  • --export — generate research/state_standalone.md by inlining pointer files (for external LLM sharing).

Usage

/research-state               # refresh state.md + propose MANUAL updates + optional README sync
/research-state --export      # generate state_standalone.md (gitignored by convention)
/research-state --max-lines 600   # --export with larger per-file inline cap (default 400)
<!-- PROJECT_INLINE_START -->
/research-state lang=en       # propose edits in a specific language
<!-- PROJECT_INLINE_END -->
argument description default
--export generate standalone bundle instead of updating state.md off
--max-lines N per-file inline cap for --export 400

| lang | output language for proposal text. The project's CLAUDE.md defines the default | project default |

Procedure

Step 1: Branch on mode

If user passed --export:

  • Run python3 research/chat/build_context.py --expand [--max-lines N]
  • Report output path + size + token estimate in 2~3 lines
  • Suggest copying/attaching the standalone file when sharing externally
  • Stop here (no MANUAL section proposals, no README sync)

Read the full file on GitHub · 131 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. 11d ago First seen · 131 lines · 0 tokens per session scan A b7f47c12e41d

Subscribe to this mod's changes

research-state is a command published in the GitHub repository Hwiyeon/claude-sisyphus-grad (59 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,557 tokens. 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.