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.
npx agentmods add commands/paiml/depyler/convergegit clone --depth 1 https://github.com/paiml/depylerWrote 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/commands/paiml/depyler/converge)<a href="https://agentmods.dev/commands/paiml/depyler/converge"><img src="https://agentmods.dev/badge/commands/paiml/depyler/converge.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00482 |
| Opus 5 | $0.00000 | $0.00241 |
| Sonnet 5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
converge 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.
What it actually says
Corpus Convergence Protocol
Run the convergence protocol from docs/prompts/converge_reprorusted_100.md.
Quick Start
Use the built-in converge command with rich progress feedback:
# Build release binary first
cargo build --release --bin depyler
# Run convergence with rich TUI progress (progress bars, sparklines)
./target/release/depyler converge --input-dir /home/noah/src/reprorusted-python-cli/examples --target-rate 80 --display rich
# CI-friendly minimal output
./target/release/depyler converge --input-dir /home/noah/src/reprorusted-python-cli/examples --target-rate 80 --display minimal
Display Modes
| Mode | Description |
|---|---|
--display rich |
TUI with progress bars and detailed cluster info (default) |
--display minimal |
Single-line CI-friendly output |
--display json |
JSON output for automation |
--display silent |
No output |
Alternative: UTOL Automated Loop
./target/release/depyler utol --corpus /home/noah/src/reprorusted-python-cli/examples --target-rate 0.80 --display rich
Quick Status Check
./target/release/depyler utol --corpus /home/noah/src/reprorusted-python-cli/examples --status
Key Commands
| Task | Command |
|---|---|
| Cache Warm | depyler cache warm --input-dir $CORPUS |
| Converge (Rich) | depyler converge --input-dir $CORPUS --target-rate 80 --display rich |
| Converge (CI) | depyler converge --input-dir $CORPUS --target-rate 80 --display minimal |
| UTOL | depyler utol --corpus $CORPUS --target-rate 0.80 --display rich |
| Status | depyler utol --corpus $CORPUS --status |
| Explain | depyler explain <file.rs> --trace <trace.json> |
Full Protocol
See: docs/prompts/converge_reprorusted_100.md
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.
- 5d ago First seen · 55 lines · 0 tokens per session scan A b9299a3d9309
converge 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 482 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.
Other commands, from other repositories
type-coverage
Vérification Couverture des Types Python.
cargo-bench
Command "cargo-bench" from olorehq/olore, covering cargo-bench(1), name, synopsis, description and working directory of benchmarks.
cargo-check
Command "cargo-check" from olorehq/olore, covering cargo-check(1), name, synopsis, description and options.
update-python-version
Update the minimum Python version requirement across the entire codebase.
execute-pydantic-ai-prp
Implement a Pydantic AI agent using the PRP file.
review
Comprehensive code review for blz changes.