dotclaude CLAUDE.md

dotclaude CLAUDE.md is an instructions file for coding agents from lacerbi/dotclaude. It costs 668 tokens per session, scanned A, original, MIT.

Instructions for Dotclaude covering shell commands, choosing agents, running local or HPC jobs, and locating the HPC launcher. HPC means high-performance computing on shared clusters.

In plain words
What is it for?
Use them to run streamed smoke tests, preserve separate logs, inspect Slurm job output, choose agents by task difficulty, and find the HPC launcher.
Why use it?
They reduce errors caused by using the wrong shell, hidden output, overwritten logs, or unsuitable agents for a task.

Instructions file

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.

agentmods
npx agentmods add instructions/lacerbi/dotclaude/claude-md
Clone the repo
git clone --depth 1 https://github.com/lacerbi/dotclaude

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 dotclaude CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lacerbi/dotclaude/claude-md.svg)](https://agentmods.dev/instructions/lacerbi/dotclaude/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lacerbi/dotclaude/claude-md"><img src="https://agentmods.dev/badge/instructions/lacerbi/dotclaude/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 668 This file is loaded in full into every session.
When invoked 668 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00668 $0.00668
Opus 5 $0.00334 $0.00334
Sonnet 5 $0.00134 $0.00134
Haiku 4.5 $0.00067 $0.00067

Measured 5d ago against content hash 32cee759c6cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dotclaude 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 5d 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.md · 26 lines

How it starts

The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shell tooling

I'm on Windows PowerShell. @'...'@ here-strings work only in the PowerShell tool, not the Bash tool (and <<'EOF' only in Bash). For multi-line text like commit messages, use repeated -m flags.

Smoke tests / long runs must stream output. Don't pipe python ... | grep — a non-TTY pipe makes Python block-buffer stdout, so nothing shows until it exits. -u (or PYTHONUNBUFFERED=1) is the key bit; have the script print(..., flush=True) on a cadence so there's something to watch.

  • Local: run unbuffered to a uniquely-named log (don't clobber a prior run): python -u script.py > runs/run_$(date +%s).log 2>&1 (background ok), then Read/tail -F it. Filter when reading (grep the file), not in the run pipe.
  • HPC: don't hand-redirect — Slurm captures each job's stdout to its own per-jobid file (so no clobber across runs). Use hpc logs <job> --once / -n N for occasional dumps, or hpc logs to follow. The script still needs periodic flush=True so the Slurm log updates before the job ends.

Agent Selection

When deploying sub-agents, calibrate agent intelligence to task complexity:

  • Haiku: Only trivial, read-only tasks requiring no interpretation (listing files, reading contents, checking if something exists). Best suited for parallelizing many simple tasks at scale.
  • Sonnet: Standard implementation, straightforward execution, mechanical checks (linting output, test pass/fail)
  • Opus: Anything requiring judgment—analysis, review, verification, planning, debugging, architectural decisions

Parallel fan-out — only one heavy-compute agent. When fanning out parallel agents (e.g. for review/doublecheck), at most ONE may run heavy compute (GPU/CPU-intensive processes: training, torch, test suites, builds). Instruct the rest to go deep but stay read-only / static-analysis (reading files, reasoning, grepping) — explicitly tell them not to run such processes. Running heavy compute in several agents at once once froze the machine. Cleanest variant: keep the single heavy slot in the main thread yourself and make the whole fan-out read-only.

Read the full file on GitHub · 26 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. 5d ago First seen · 26 lines · 668 tokens per session scan A 32cee759c6cd

Subscribe to this mod's changes

dotclaude CLAUDE.md is an instructions file published in the GitHub repository lacerbi/dotclaude (2 stars, last pushed 5d ago), licensed MIT. It adds 668 tokens to every session, about $0.0033 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 2026-08-31.