What is improve-compile-rate?

An autonomous work plan for improving Depyler’s single-shot compile rate—the share of Python examples that compile successfully into Rust on the first attempt—to 80% on a named example collection.

Use it to find the most common conversion errors, inspect failing Python and Rust, change Depyler, run its tests and checks, and measure the updated compile rate.

It provides a repeatable loop for measuring failures, investigating the generated code, fixing the compiler, and checking whether the result improved. This avoids judging progress without measurements.

How paiml/depyler configures Claude Code

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/improve-compile-rate.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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/paiml/depyler/improve-compile-rate/github.svg)](https://agentmods.dev/commands/paiml/depyler/improve-compile-rate)

Your own site

<a href="https://agentmods.dev/commands/paiml/depyler/improve-compile-rate"><img src="https://agentmods.dev/badge/commands/paiml/depyler/improve-compile-rate/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/paiml/depyler/improve-compile-rate"><img src="https://agentmods.dev/badge/commands/paiml/depyler/improve-compile-rate.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 578 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	$0.00578
Opus 5.5	$0.00000	$0.00231
Sonnet 5.5	$0.00000	$0.00116
Haiku 4.5	$0.00000	$0.00058

Measured 2mo ago against content hash c61192634bc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

improve-compile-rate 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/improve-compile-rate.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Depyler Single-Shot Compile Rate: Autonomous Improvement Loop

Goal

Reach 80% single-shot compile rate on reprorusted-python-cli corpus. Work through bugs autonomously.

Measure First

cd /home/noah/src/reprorusted-python-cli
make corpus-retranspile
make corpus-e2e-rate

If >= 80%, report success and stop.

Iteration Loop

1. Find Top Error

cd /home/noah/src/reprorusted-python-cli
uv run python scripts/measure_compile_rate.py --json | jq -r '.failing[].error' | sort | uniq -c | sort -rn | head -5

2. Investigate

Find a failing example, read its Python source and generated Rust. Understand the gap.

3. Fix in depyler

Locations:

Module mappings → crates/depyler-core/src/direct_rules.rs
Type mappings → crates/depyler-core/src/type_mapper.rs
Expr generation → crates/depyler-core/src/rust_gen/expr_gen.rs
Cargo.toml → crates/depyler-core/src/cargo_toml_gen.rs

4. Validate

cd /home/noah/src/depyler
cargo test -p depyler-core
cargo clippy -p depyler-core -- -D warnings

If fails: git checkout -- . and try different approach.

5. Measure Impact

cargo install --path crates/depyler --force
cd /home/noah/src/reprorusted-python-cli
make corpus-retranspile && make corpus-e2e-rate

If regression: rollback. If no change: still commit (may help other metrics).

6. Commit

git add -A && git commit -m "fix(core): [description] (Refs #193)"

7. Repeat until 80%

Bug Recovery

Issue	Action
Tests fail	Rollback, try narrower fix
Regression	Rollback, add guards
Same error 3x	Skip, move to next pattern
Transpile drops	Rollback, fix is too broad

Priority Errors (from corpus analysis)

cannot find value os - 16 files
cannot find function date - 10 files
expected value, found crate tempfile - 8 files
SCRIPT defined multiple times - 5 files

Exit

SUCCESS: Rate >= 80%
STUCK: No progress 5 iterations
BLOCKED: Can't fix failing tests

Read the full file on GitHub · 74 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 · 74 lines · 0 tokens per session scan A c61192634bc1

Subscribe to this mod's changes

improve-compile-rate is a command published in the GitHub repository paiml/depyler (366 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 578 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.

Languages Planning Python Rust conversion mcp port pythontorust

improve-compile-rate next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
improve-compile-ratepaiml/depyler	Command	366	yesterday	MIT	A	0	Claude Code
indexGoldziher/spikard	Command	124	3d ago	MIT	A	0	Claude Code
type-coverageTheBeardedBearSAS/claude-craft	Command	107	3d ago	MIT	A	8	Claude Code
package-reviewoborchers/fractional-cto	Command	36	12d ago	MIT	A	41	Claude Code
reviewoutfitter-dev/blz	Command	28	2mo ago	MIT	A	8	Claude Code
fastapimfmezger/ai_agent_dotfiles	Command	7	3mo ago	MIT	A	84	Claude Code, Gemini CLI
docskikakkz/wait-agent	Command	24	19d ago	none	A	9	Claude Code

depyler: Command for Claude Code