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.
curl -O https://raw.githubusercontent.com/Hwiyeon/claude-sisyphus-grad/main/CLAUDE.mdgit clone --depth 1 https://github.com/Hwiyeon/claude-sisyphus-gradWrote 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.
[](https://agentmods.dev/instructions/hwiyeon/claude-sisyphus-grad/claude-md)<a href="https://agentmods.dev/instructions/hwiyeon/claude-sisyphus-grad/claude-md"><img src="https://agentmods.dev/badge/instructions/hwiyeon/claude-sisyphus-grad/claude-md/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.
<a href="https://agentmods.dev/instructions/hwiyeon/claude-sisyphus-grad/claude-md"><img src="https://agentmods.dev/badge/instructions/hwiyeon/claude-sisyphus-grad/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00549 | $0.00549 |
| Opus 5 | $0.00275 | $0.00275 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
claude-sisyphus-grad CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-sisyphus-grad — Project Configuration
Required Settings (modify to fit your project)
Experiment Environment
CONDA_ENV=myenv # conda env name (default for train command env arg)
Research Directory Settings
# If research/ is a separate git repo:
# git -C research remote -v to verify
# If not a separate repo, use regular git add/push
Metric Query Settings (optional)
# Using wandb: no extra config needed (prompts use wandb API by default)
# Using custom logging: set env vars below
# METRIC_FETCH_CMD="python scripts/fetch_metrics.py --step {last_step}"
# EPOCH_LOG_PATTERN="Epoch {n}/{total} | loss={loss} | val={val}"
GitHub Sync Settings (optional)
# Override research/ sync command (default: git push)
# RESEARCH_SYNC_CMD="bash scripts/my_sync.sh"
Git Branch Rules
- Always create a new branch for each feature/task
- branch naming:
feat/<feature-name>,fix/<bug-name>,train/<experiment>/exp{N}-code-mod - Merge into main when done, delete the branch afterward
- Do not commit directly to main
Experiment Automation
- For DL/ML experiment automation: use the
/traincommand - Detailed protocol: see
.claude/commands/train.md
Research Notes
- Always read
research/CLAUDE.mdbefore starting research discussions - Check
research/README.mdfor current research status - Create
research/logs/YYYY-MM-DD/log.mdat the start of each day's discussion - Use the
/discusscommand to start context-aware research discussions
Project Customization Points
Adjust the following to fit your project's characteristics:
1. Reviewer Role Adjustment (.claude/prompts/train-review-pipeline.md)
Default: A(stats/metrics), B(algorithm), C(data), D(Feasibility), E(supplement), F(moderator), G(Research Innovator) Modify, add, or remove reviewer roles based on your domain.
2. Abort Condition Adjustment (.claude/prompts/train-monitor.md)
Default abort conditions: NaN/Inf, val_loss diverges >3x Recommended to adjust for your project's key metric.
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.
- 11d ago First seen · 65 lines · 549 tokens per session scan A 831c4c2c41b7
claude-sisyphus-grad CLAUDE.md is an instructions file published in the GitHub repository Hwiyeon/claude-sisyphus-grad (59 stars, last pushed 3mo ago), licensed MIT. It adds 549 tokens to every session, about $0.0027 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).