depyler: Command for Claude Code

.claude/commands/overnight-80.md

overnight-80 is a command for Claude Code from paiml/depyler. It costs 0 tokens per session (2,010 once invoked), scanned A, original, MIT.

An overnight improvement loop that repeatedly measures a Rust project's compile results, fixes the most important errors, and stops when the target is reached.

In plain words
What is it for?
Use it with the Depyler project to prepare the repository, run up to 50 improvement iterations, test and build the code, and log progress toward 80% single-shot compilation.
Why use it?
It lets a long-running process continue through repeated build-and-fix cycles instead of requiring manual attention after every attempt.

Command for Claude Code

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

This is paiml/depyler's own configuration. It tells Claude Code how to work on depyler 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 depyler configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/noah/src/depyler.

Reuse

Borrowing it

Nothing to install: this file belongs to paiml/depyler. 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/paiml/depyler/main/.claude/commands/overnight-80.md
Clone the repo
git clone --depth 1 https://github.com/paiml/depyler

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 overnight-80

README.md
[![agentmods](https://agentmods.dev/badge/commands/paiml/depyler/overnight-80.svg)](https://agentmods.dev/commands/paiml/depyler/overnight-80)
Your own site
<a href="https://agentmods.dev/commands/paiml/depyler/overnight-80"><img src="https://agentmods.dev/badge/commands/paiml/depyler/overnight-80.svg" alt="Measured on agentmods" 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 2,010 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 $0.02010
Opus 5 $0.00000 $0.01005
Sonnet 5 $0.00000 $0.00402
Haiku 4.5 $0.00000 $0.00201

Measured 7d ago against content hash 5eec10611f06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

overnight-80 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 7d 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/overnight-80.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overnight: Reach 80% Single-Shot Compile

Autonomous improvement loop designed to run all night. Handles ANY starting condition.

Pre-Flight: Handle Any State

cd /home/noah/src/depyler

# Check for uncommitted work - commit it first
if [ -n "$(git status --porcelain)" ]; then
    echo "Found uncommitted changes - committing first"
    cargo test -p depyler-core --quiet
    if [ $? -eq 0 ]; then
        git add -A
        git commit -m "wip: Uncommitted changes from previous session (Refs #193)"
    else
        echo "Tests fail with uncommitted changes - stashing"
        git stash push -m "overnight-stash-$(date +%H%M%S)"
    fi
fi

# Ensure we have latest code
git pull --rebase origin main 2>/dev/null || true

# Ensure depyler is built and installed
cargo build --release -p depyler 2>/dev/null
cargo install --path crates/depyler --force 2>/dev/null

Setup

export LOG="/tmp/depyler-overnight-$(date +%Y%m%d).log"
echo "=== Started $(date) ===" >> $LOG
echo "Git HEAD: $(git rev-parse --short HEAD)" >> $LOG

Main Loop (max 50 iterations)

for iteration in 1..50:
    1. Measure
    2. If >= 80%: SUCCESS, stop
    3. Find highest-impact error pattern
    4. Implement minimal fix
    5. Validate (tests + clippy)
    6. If fail: rollback, try different approach or skip pattern
    7. Measure delta
    8. If improved: commit
    9. If stuck 3x on same pattern: skip, move to next
    10. Log everything

Phase 1: Measure State

cd /home/noah/src/reprorusted-python-cli
make corpus-retranspile 2>&1 | tail -5
RESULT=$(uv run python scripts/measure_compile_rate.py --json)
RATE=$(echo $RESULT | jq -r '.rate')
echo "[$(date)] Rate: $RATE%" >> $LOG

if (( $(echo "$RATE >= 80" | bc -l) )); then
    echo "SUCCESS at $RATE%" >> $LOG
    exit 0
fi

Phase 2: Identify Top Error (Smart Selection)

# Get error frequency with file counts
uv run python scripts/measure_compile_rate.py --json | \
  jq -r '.failing[] | .error' | \
  sed 's/error\[E[0-9]*\]: //' | \
  sort | uniq -c | sort -rn | head -10

Read the full file on GitHub · 242 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. 7d ago First seen · 242 lines · 0 tokens per session scan A 5eec10611f06

Subscribe to this mod's changes

overnight-80 is a command published in the GitHub repository paiml/depyler (358 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,010 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.