A command that runs a one-time, multi-agent review of experiment results outside the project's training loop.

Use it with an experiment's results JSON file and detail Markdown file. Optional settings control review cycles, reference files, and output language.

It provides a separate review step when you want feedback on an experiment without running the full training process.

How Hwiyeon/claude-sisyphus-grad configures Claude Code

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/review.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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/hwiyeon/claude-sisyphus-grad/review/github.svg)](https://agentmods.dev/commands/hwiyeon/claude-sisyphus-grad/review)

Your own site

<a href="https://agentmods.dev/commands/hwiyeon/claude-sisyphus-grad/review"><img src="https://agentmods.dev/badge/commands/hwiyeon/claude-sisyphus-grad/review/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/hwiyeon/claude-sisyphus-grad/review"><img src="https://agentmods.dev/badge/commands/hwiyeon/claude-sisyphus-grad/review.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 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00557
Opus 5.5	$0.00000	$0.00223
Sonnet 5.5	$0.00000	$0.00111
Haiku 4.5	$0.00000	$0.00056

Measured 2mo ago against content hash 091a509bfee8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review 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 2mo 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/review.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Standalone Review Command

Runs the multi-agent review pipeline independently on experiment results. Can be used standalone outside the /train loop; performs a one-time review without ralph-loop integration.

Usage

/review results=path/to/experiment_N.json detail=path/to/experiment_N_detail.md [review_cycles=1] [config=...] [script=...]

Arguments

argument	description	default
`results`	path to experiment result JSON file	required
`detail`	path to experiment detail MD file	required
`review_cycles`	number of G→round2→round3→Judge cycle repetitions	1
`config`	config file path (passed to reviewers as reference)	optional
`script`	training script path (passed to reviewers as reference)	optional

| lang | output language for review output (ko, en, etc.). The project's CLAUDE.md defines the default | project default |

Procedure

Step 1: Parse and Validate Arguments

Parse arguments from $ARGUMENTS.

Verify that results and detail files exist

Infer metric cache path: cache/metric_cache.jsonl in the same session directory as detail file

Print parsed values for user confirmation

Step 2: Load Review Pipeline Module

Read .claude/prompts/train-review-pipeline.md to load review rules.

Step 3: Run Review

Run multi-agent review per train-review-pipeline.md rules:

Input mapping:
- experiment_n: extracted from filename (e.g., experiment_3.json → 3)
- detail_file: detail argument
- results_file: results argument

metric_cache: inferred path (skip if not found)

review_cycles: argument value
config, script: argument values (not passed to reviewers if absent)

Step 4: Output Results

Output Judge decision directly to user
No session_continuation.json manipulation
No ralph-loop integration
Review content is recorded in the detail file (handled by the review pipeline scribe)

Read the full file on GitHub · 71 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.

2mo ago First seen · 71 lines · 0 tokens per session scan A 091a509bfee8

Subscribe to this mod's changes

review is a command published in the GitHub repository Hwiyeon/claude-sisyphus-grad (58 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 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.

Research

review next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
reviewHwiyeon/claude-sisyphus-grad	Command	58	5mo ago	MIT	A	0	Claude Code
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code

claude-sisyphus-grad: Command for Claude Code